%%% -*-BibTeX-*-
%%% ====================================================================
%%%  BibTeX-file{
%%%     author          = "Nelson H. F. Beebe",
%%%     version         = "1.10",
%%%     date            = "13 December 2013",
%%%     time            = "06:36:49 MST",
%%%     filename        = "vldbe.bib",
%%%     address         = "University of Utah
%%%                        Department of Mathematics, 110 LCB
%%%                        155 S 1400 E RM 233
%%%                        Salt Lake City, UT 84112-0090
%%%                        USA",
%%%     telephone       = "+1 801 581 5254",
%%%     FAX             = "+1 801 581 4148",
%%%     URL             = "http://www.math.utah.edu/~beebe",
%%%     checksum        = "17349 29481 147234 1363252",
%%%     email           = "beebe at math.utah.edu, beebe at acm.org,
%%%                        beebe at computer.org (Internet)",
%%%     codetable       = "ISO/ASCII",
%%%     keywords        = "BibTeX; bibliography; Very Large Data Bases;
%%%                        Proceedings of the VLDB Endowment",
%%%     license         = "public domain",
%%%     supported       = "yes",
%%%     docstring       = "This is a COMPLETE bibliography of
%%%                        publications in the Proceedings of the VLDB
%%%                        Endowment (CODEN unknown, ISSN 2150-8097).
%%%
%%%                        The journal has a Web site at
%%%
%%%                            http://portal.acm.org/citation.cfm?id=J1174
%%%
%%%                        At version 1.10, the year coverage looked
%%%                        like this:
%%%
%%%                             2008 ( 169)    2010 ( 193)    2012 ( 187)
%%%                             2009 ( 167)    2011 (  75)    2013 ( 210)
%%%
%%%                             Article:       1001
%%%
%%%                             Total entries: 1001
%%%
%%%                        The checksum field above contains a CRC-16
%%%                        checksum as the first value, followed by the
%%%                        equivalent of the standard UNIX wc (word
%%%                        count) utility output of lines, words, and
%%%                        characters.  This is produced by Robert
%%%                        Solovay's checksum utility.",
%%%  }
%%% ====================================================================

@Preamble{
    "\ifx \undefined \k \let \k = \c \fi" #
    "\ifx \undefined \ocirc  \def \ocirc #1{{\accent'27#1}}\fi"
}

%%% ====================================================================
%%% Acknowledgement abbreviations:

@String{ack-nhfb = "Nelson H. F. Beebe,
                    University of Utah,
                    Department of Mathematics, 110 LCB,
                    155 S 1400 E RM 233,
                    Salt Lake City, UT 84112-0090, USA,
                    Tel: +1 801 581 5254,
                    FAX: +1 801 581 4148,
                    e-mail: \path|beebe@math.utah.edu|,
                            \path|beebe@acm.org|,
                            \path|beebe@computer.org| (Internet),
                    URL: \path|http://www.math.utah.edu/~beebe/|"}

%%% ====================================================================
%%% Journal abbreviations:

@String{j-PROC-VLDB-ENDOWMENT = "Proceedings of the VLDB Endowment"}

%%% ====================================================================
%%% Bibliography entries, sorted in publication order:

@Article{Hill:2008:TMO,
  author =       "Mark D. Hill",
  title =        "Is transactional memory an oxymoron?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1--1",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453858",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zobel:2008:DSH,
  author =       "Justin Zobel",
  title =        "Databases and the silification of health",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "2--2",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453859",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Blott:2008:WWH,
  author =       "Stephen Blott and Roger Weber",
  title =        "What's wrong with high-dimensional similarity
                 search?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "3--3",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453861",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bruno:2008:CPD,
  author =       "Nicolas Bruno and Surajit Chaudhuri",
  title =        "Constrained physical design tuning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "4--15",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453863",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kementsietsidis:2008:SMQ,
  author =       "Anastasios Kementsietsidis and Frank Neven and Dieter
                 Van de Craen and Stijn Vansummeren",
  title =        "Scalable multi-query optimization for exploratory
                 queries over federated scientific databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "16--27",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453864",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{DeWitt:2008:CIC,
  author =       "David J. DeWitt and Erik Paulson and Eric Robinson and
                 Jeffrey Naughton and Joshua Royalty and Srinath Shankar
                 and Andrew Krioukov",
  title =        "{Clustera}: an integrated computation and data
                 management system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "28--41",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453865",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheung:2008:PPE,
  author =       "Alvin Cheung and Samuel Madden",
  title =        "Performance profiling with {EndoScope}, an
                 acquisitional software monitoring framework",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "42--53",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453866",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bar-Yossef:2008:MSE,
  author =       "Ziv Bar-Yossef and Maxim Gurevich",
  title =        "Mining search engine query logs via suggestion
                 sampling",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "54--65",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453868",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Akdere:2008:PBC,
  author =       "Mert Akdere and U{\u{g}}ur {\c{C}}etintemel and Nesime
                 Tatbul",
  title =        "Plan-based complex event detection across distributed
                 sources",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "66--77",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453869",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lachmann:2008:FRP,
  author =       "Alexander Lachmann and Mirek Riedewald",
  title =        "Finding relevant patterns in bursty sequences",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "78--89",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453870",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheng:2008:CLW,
  author =       "Hao Cheng and Kien A. Hua and Khanh Vu",
  title =        "Constrained locally weighted clustering",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "90--101",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453871",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hay:2008:RSR,
  author =       "Michael Hay and Gerome Miklau and David Jensen and Don
                 Towsley and Philipp Weis",
  title =        "Resisting structural re-identification in anonymized
                 social networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "102--114",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453873",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Terrovitis:2008:PPA,
  author =       "Manolis Terrovitis and Nikos Mamoulis and Panos
                 Kalnis",
  title =        "Privacy-preserving anonymization of set-valued data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "115--125",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453874",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pang:2008:AQR,
  author =       "HweeHwa Pang and Kyriakos Mouratidis",
  title =        "Authenticating the query results of text search
                 engines",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "126--137",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453875",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kundu:2008:SST,
  author =       "Ashish Kundu and Elisa Bertino",
  title =        "Structural signatures for tree data structures",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "138--150",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453876",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Roitman:2008:MDC,
  author =       "Haggai Roitman and David Carmel and Elad Yom-Tov",
  title =        "Maintaining dynamic channel profiles on the {Web}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "151--162",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453878",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2008:WDD,
  author =       "Fan Yang and Nitin Gupta and Chavdar Botev and
                 Elizabeth F. Churchill and George Levchenko and Jayavel
                 Shanmugasundaram",
  title =        "{WYSIWYG} development of data driven {Web}
                 applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "163--175",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453879",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Baykan:2008:WPL,
  author =       "Eda Baykan and Monika Henzinger and Ingmar Weber",
  title =        "{Web} page language identification based on {URLs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "176--187",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453880",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Han:2008:PQO,
  author =       "Wook-Shin Han and Wooseong Kwak and Jinsoo Lee and Guy
                 M. Lohman and Volker Markl",
  title =        "Parallelizing query optimization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "188--200",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453882",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hadjieleftheriou:2008:HSS,
  author =       "Marios Hadjieleftheriou and Xiaohui Yu and Nick Koudas
                 and Divesh Srivastava",
  title =        "Hashed samples: selectivity estimators for set
                 similarity selection queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "201--212",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453883",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cohen:2008:TEU,
  author =       "Edith Cohen and Haim Kaplan",
  title =        "Tighter estimation using bottom $k$ sketches",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "213--229",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453884",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alexe:2008:STB,
  author =       "Bogdan Alexe and Wang-Chiew Tan and Yannis
                 Velegrakis",
  title =        "{STBenchmark}: towards a benchmark for mapping
                 systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "230--244",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453886",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Katsis:2008:ISR,
  author =       "Yannis Katsis and Alin Deutsch and Yannis
                 Papakonstantinou",
  title =        "Interactive source registration in community-oriented
                 information integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "245--259",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453887",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hernandez:2008:DED,
  author =       "Mauricio A. Hern{\'a}ndez and Paolo Papotti and
                 Wang-Chiew Tan",
  title =        "Data exchange with data-metadata translations",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "260--273",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453888",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2008:OPN,
  author =       "Jin Li and Kristin Tufte and Vladislav Shkapenyuk and
                 Vassilis Papadimos and Theodore Johnson and David
                 Maier",
  title =        "Out-of-order processing: a new architecture for
                 high-performance stream systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "274--288",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453890",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Han:2008:SET,
  author =       "Wook-Shin Han and Haifeng Jiang and Howard Ho and
                 Quanzhong Li",
  title =        "{StreamTX}: extracting tuples from streaming {XML}
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "289--300",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453891",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jin:2008:SWT,
  author =       "Cheqing Jin and Ke Yi and Lei Chen and Jeffrey Xu Yu
                 and Xuemin Lin",
  title =        "Sliding-window top-$k$ queries on uncertain streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "301--312",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453892",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koch:2008:CPD,
  author =       "Christoph Koch and Dan Olteanu",
  title =        "Conditioning probabilistic databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "313--325",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453894",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Beskales:2008:EST,
  author =       "George Beskales and Mohamed A. Soliman and Ihab F.
                 Ilyas",
  title =        "Efficient search for the top-$k$ probable nearest
                 neighbors in uncertain databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "326--339",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453895",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2008:BML,
  author =       "Daisy Zhe Wang and Eirinaios Michelakis and Minos
                 Garofalakis and Joseph M. Hellerstein",
  title =        "{BayesStore}: managing large, uncertain data
                 repositories with probabilistic graphical models",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "340--351",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453896",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deutch:2008:TIT,
  author =       "Daniel Deutch and Tova Milo",
  title =        "Type inference and type checking for queries on
                 execution traces",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "352--363",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453898",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shang:2008:TVH,
  author =       "Haichuan Shang and Ying Zhang and Xuemin Lin and
                 Jeffrey Xu Yu",
  title =        "Taming verification hardness: an efficient algorithm
                 for testing subgraph isomorphism",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "364--375",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453899",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Golab:2008:GNO,
  author =       "Lukasz Golab and Howard Karloff and Flip Korn and
                 Divesh Srivastava and Bei Yu",
  title =        "On generating near-optimal tableaux for conditional
                 functional dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "376--390",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453900",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2008:PFD,
  author =       "Wenfei Fan and Shuai Ma and Yanli Hu and Jie Liu and
                 Yinghui Wu",
  title =        "Propagating functional dependencies with conditions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "391--407",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453901",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Antonellis:2008:SQR,
  author =       "Ioannis Antonellis and Hector Garcia Molina and Chi
                 Chao Chang",
  title =        "{Simrank++}: query rewriting through link analysis of
                 the click graph",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "408--421",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453903",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lizorkin:2008:AEO,
  author =       "Dmitry Lizorkin and Pavel Velikhov and Maxim Grinev
                 and Denis Turdakov",
  title =        "Accuracy estimate and optimization techniques for
                 {SimRank} computation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "422--433",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453904",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chandramouli:2008:EES,
  author =       "Badrish Chandramouli and Jun Yang",
  title =        "End-to-end support for joins in large-scale
                 publish\slash subscribe systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "434--450",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453905",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Machanavajjhala:2008:SRP,
  author =       "Ashwin Machanavajjhala and Erik Vee and Minos
                 Garofalakis and Jayavel Shanmugasundaram",
  title =        "Scalable ranked publish\slash subscribe",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "451--462",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453906",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Teubner:2008:DCF,
  author =       "Jens Teubner and Torsten Grust and Sebastian Maneth
                 and Sherif Sakr",
  title =        "Dependable cardinality forecasts for {XQuery}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "463--477",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453908",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2008:HBS,
  author =       "Hongzhi Wang and Jianzhong Li and Jizhou Luo and Hong
                 Gao",
  title =        "Hash-base subgraph query processing method for
                 graph-structured {XML} documents",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "478--489",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453909",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cohen:2008:GXS,
  author =       "Sara Cohen",
  title =        "Generating {XML} structure using examples and
                 constraints",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "490--501",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453910",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Holloway:2008:ROD,
  author =       "Allison L. Holloway and David J. DeWitt",
  title =        "Read-optimized databases, in depth",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "502--513",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453912",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koltsidas:2008:FSL,
  author =       "Ioannis Koltsidas and Stratis D. Viglas",
  title =        "Flashing up the storage layer",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "514--525",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453913",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sears:2008:RCL,
  author =       "Russell Sears and Mark Callaghan and Eric Brewer",
  title =        "{Rose}: compressed, log-structured replication",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "526--537",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453914",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cafarella:2008:WEP,
  author =       "Michael J. Cafarella and Alon Halevy and Daisy Zhe
                 Wang and Eugene Wu and Yang Zhang",
  title =        "{WebTables}: exploring the power of tables on the
                 {Web}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "538--549",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453916",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Garrod:2008:SQR,
  author =       "Charles Garrod and Amit Manjhi and Anastasia Ailamaki
                 and Bruce Maggs and Todd Mowry and Christopher Olston
                 and Anthony Tomasic",
  title =        "Scalable query result caching for {Web} applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "550--561",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453917",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Braga:2008:OMD,
  author =       "Daniele Braga and Stefano Ceri and Florian Daniel and
                 Davide Martinenghi",
  title =        "Optimization of multi-domain queries on the {Web}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "562--573",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453918",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kwon:2008:FTS,
  author =       "YongChul Kwon and Magdalena Balazinska and Albert
                 Greenberg",
  title =        "Fault-tolerant stream processing using a distributed,
                 replicated file system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "574--585",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453920",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yeh:2008:LLW,
  author =       "Mi-Yen Yeh and Kun-Lung Wu and Philip S. Yu and
                 Ming-Syan Chen",
  title =        "{LeeWave}: level-wise distribution of wavelet
                 coefficients for processing $k$ {NN} queries over
                 distributed streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "586--597",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453921",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Aguilera:2008:PSD,
  author =       "Marcos K. Aguilera and Wojciech Golab and Mehul A.
                 Shah",
  title =        "A practical scalable distributed {B-tree}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "598--609",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453922",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Qiao:2008:MMS,
  author =       "Lin Qiao and Vijayshankar Raman and Frederick Reiss
                 and Peter J. Haas and Guy M. Lohman",
  title =        "Main-memory scan sharing for multi-core {CPUs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "610--621",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453924",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Johnson:2008:RWP,
  author =       "Ryan Johnson and Vijayshankar Raman and Richard Sidle
                 and Garret Swart",
  title =        "Row-wise parallel predicate evaluation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "622--634",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453925",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Soundararajan:2008:DPC,
  author =       "Gokul Soundararajan and Jin Chen and Mohamed A. Sharaf
                 and Cristiana Amza",
  title =        "Dynamic partitioning of the cache hierarchy in shared
                 data centers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "635--646",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453926",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Neumann:2008:RRS,
  author =       "Thomas Neumann and Gerhard Weikum",
  title =        "{RDF-3X}: a {RISC}-style engine for {RDF}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "647--659",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453927",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Simitsis:2008:MCE,
  author =       "Alkis Simitsis and Akanksha Baid and Yannis Sismanis
                 and Berthold Reinwald",
  title =        "Multidimensional content {eXploration}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "660--671",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453929",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fontoura:2008:RTS,
  author =       "Marcus Fontoura and Vanja Josifovski and Ravi Kumar
                 and Christopher Olston and Andrew Tomkins and Sergei
                 Vassilvitskii",
  title =        "Relaxation in text search using taxonomies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "672--683",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453930",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nguyen:2008:LEF,
  author =       "Hoa Nguyen and Thanh Nguyen and Juliana Freire",
  title =        "Learning to extract form labels",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "684--694",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453931",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jayapandian:2008:ACF,
  author =       "Magesh Jayapandian and H. V. Jagadish",
  title =        "Automated creation of a forms-based database query
                 interface",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "695--709",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453932",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yahia:2008:ENA,
  author =       "Sihem Amer Yahia and Michael Benedikt and Laks V. S.
                 Lakshmanan and Julia Stoyanovich",
  title =        "Efficient network aware search in collaborative
                 tagging sites",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "710--721",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453934",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheng:2008:CUD,
  author =       "Reynold Cheng and Jinchuan Chen and Xike Xie",
  title =        "Cleaning uncertain data with quality guarantees",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "722--735",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453935",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Huang:2008:PNA,
  author =       "Jiansheng Huang and Ting Chen and AnHai Doan and
                 Jeffrey F. Naughton",
  title =        "On the provenance of non-answers to queries over
                 extracted data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "736--747",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453936",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhu:2008:DAP,
  author =       "Shenghuo Zhu and Tao Li and Zhiyuan Chen and Dingding
                 Wang and Yihong Gong",
  title =        "Dynamic active probing of helpdesk databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "748--760",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453937",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Curino:2008:GDS,
  author =       "Carlo A. Curino and Hyun J. Moon and Carlo Zaniolo",
  title =        "Graceful database schema evolution: the {PRISM}
                 workbench",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "761--772",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453939",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chai:2008:ARD,
  author =       "Xiaoyong Chai and Mayssam Sayyadian and AnHai Doan and
                 Arnon Rosenthal and Len Seligman",
  title =        "Analyzing and revising data integration schemas to
                 improve their matchability",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "773--784",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453940",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Talukdar:2008:LCD,
  author =       "Partha Pratim Talukdar and Marie Jacob and Muhammad
                 Salman Mehmood and Koby Crammer and Zachary G. Ives and
                 Fernando Pereira and Sudipto Guha",
  title =        "Learning to create data-integrating queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "785--796",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453941",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Re:2008:ALP,
  author =       "Christopher R{\'e} and Dan Suciu",
  title =        "Approximate lineage for probabilistic databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "797--808",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453943",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sen:2008:ESC,
  author =       "Prithviraj Sen and Amol Deshpande and Lise Getoor",
  title =        "Exploiting shared correlations in probabilistic
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "809--820",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453944",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rastogi:2008:ACU,
  author =       "Vibhor Rastogi and Dan Suciu and Evan Welbourne",
  title =        "Access control over uncertain data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "821--832",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453945",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cormode:2008:ABG,
  author =       "Graham Cormode and Divesh Srivastava and Ting Yu and
                 Qing Zhang",
  title =        "Anonymizing bipartite graph data using safe
                 groupings",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "833--844",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453947",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bu:2008:PPS,
  author =       "Yingyi Bu and Ada Wai Chee Fu and Raymond Chi Wing
                 Wong and Lei Chen and Jiuyong Li",
  title =        "Privacy preserving serial data publishing by role
                 composition",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "845--856",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453948",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xiao:2008:OPQ,
  author =       "Xiaokui Xiao and Yufei Tao",
  title =        "Output perturbation with query relaxation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "857--869",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453949",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lomet:2008:TTI,
  author =       "David Lomet and Mingsheng Hong and Rimma Nehme and Rui
                 Zhang",
  title =        "Transaction time indexing with version compression",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "870--881",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453951",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Moon:2008:MQT,
  author =       "Hyun J. Moon and Carlo A. Curino and Alin Deutsch and
                 Chien-Yi Hou and Carlo Zaniolo",
  title =        "Managing and querying transaction-time databases under
                 schema evolution",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "882--895",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453952",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sherkat:2008:EST,
  author =       "Reza Sherkat and Davood Rafiei",
  title =        "On efficiently searching trajectories and archival
                 data for historical similarities",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "896--908",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453953",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pu:2008:KQC,
  author =       "Ken Q. Pu and Xiaohui Yu",
  title =        "Keyword query cleaning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "909--920",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453955",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2008:RIR,
  author =       "Ziyang Liu and Yi Cher",
  title =        "Reasoning and identifying relevant matches for {XML}
                 keyword search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "921--932",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453956",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xiao:2008:EJE,
  author =       "Chuan Xiao and Wei Wang and Xuemin Lin",
  title =        "{Ed-Join}: an efficient algorithm for similarity joins
                 with edit distance constraints",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "933--944",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453957",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agrawal:2008:SAH,
  author =       "Sanjay Agrawal and Kaushik Chakrabarti and Surajit
                 Chaudhuri and Venkatesh Ganti",
  title =        "Scalable ad-hoc entity extraction from text
                 collections",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "945--957",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453958",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agrawal:2008:SSS,
  author =       "Parag Agrawal and Daniel Kifer and Christopher
                 Olston",
  title =        "Scheduling shared scans of large data files",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "958--969",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453960",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nath:2008:OMV,
  author =       "Suman Nath and Phillip B. Gibbons",
  title =        "Online maintenance of very large random samples on
                 flash storage",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "970--983",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453961",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ge:2008:SLA,
  author =       "Tingjian Ge and Stan Zdonik",
  title =        "A skip-list approach for efficiently processing
                 forecasting queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "984--995",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453962",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Phan:2008:RRF,
  author =       "Thomas Phan and Wen-Syan Li",
  title =        "A request-routing framework for {SOA}-based enterprise
                 computing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "996--1007",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453963",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Weiss:2008:HSI,
  author =       "Cathrin Weiss and Panagiotis Karras and Abraham
                 Bernstein",
  title =        "{Hexastore}: sextuple indexing for {Semantic Web} data
                 management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1008--1019",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453965",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shahabi:2008:ILS,
  author =       "Cyrus Shahabi and Lu-An Tang and Songhua Xing",
  title =        "Indexing land surface for efficient {kNN} query",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1020--1031",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453966",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wong:2008:ESQ,
  author =       "Raymond Chi-Wing Wong and Ada Wai-Chee Fu and Jian Pei
                 and Yip Sing Ho and Tai Wong and Yubao Liu",
  title =        "Efficient skyline querying with variable user
                 preferences on nominal attributes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1032--1043",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453967",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guo:2008:ETP,
  author =       "Lin Guo and Sihem Amer Yahia and Raghu Ramakrishnan
                 and Jayavel Shanmugasundaram and Utkarsh Srivastava and
                 Erik Vee",
  title =        "Efficient top-$k$ processing over query-dependent
                 functions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1044--1055",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453968",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2008:FER,
  author =       "Wei Wu and Fei Yang and Chee-Yong Chan and Kian-Lee
                 Tan",
  title =        "{FINCH}: evaluating reverse $k$-Nearest-Neighbor
                 queries on location data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1056--1067",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453970",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jeung:2008:DCT,
  author =       "Hoyoung Jeung and Man Lung Yiu and Xiaofang Zhou and
                 Christian S. Jensen and Heng Tao Shen",
  title =        "Discovery of convoys in trajectory databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1068--1080",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453971",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2008:TTC,
  author =       "Jae-Gil Lee and Jiawei Han and Xiaolei Li and Hector
                 Gonzalez",
  title =        "{TraClass}: trajectory classification using
                 hierarchical region-based and trajectory-based
                 clustering",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1081--1094",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453972",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nutanong:2008:VDQ,
  author =       "Sarana Nutanong and Rui Zhang and Egemen Tanin and
                 Lars Kulik",
  title =        "The {V*-Diagram}: a query-dependent approach to moving
                 {KNN} queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1095--1106",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453973",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guravannavar:2008:RPB,
  author =       "Ravindra Guravannavar and S. Sudarshan",
  title =        "Rewriting procedures for batched bindings",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1107--1123",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453975",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{D:2008:IRP,
  author =       "Harish D. and Pooja N. Darera and Jayant R. Haritsa",
  title =        "Identifying robust plans through plan diagram
                 reduction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1124--1140",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453976",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaudhuri:2008:PYG,
  author =       "Surajit Chaudhuri and Vivek Narasayya and Ravi
                 Ramamurthy",
  title =        "A pay-as-you-go framework for query execution
                 feedback",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1141--1152",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453977",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Condie:2008:ERM,
  author =       "Tyson Condie and David Chu and Joseph M. Hellerstein
                 and Petros Maniatis",
  title =        "Evita raced: metacompilation for declarative
                 networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1153--1165",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453978",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chiang:2008:DDQ,
  author =       "Fei Chiang and Ren{\'e}e J. Miller",
  title =        "Discovering data quality rules",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1166--1177",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453980",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2008:MNR,
  author =       "Xiang Zhang and Feng Pan and Wei Wang and Andrew
                 Nobel",
  title =        "Mining non-redundant high order correlations in binary
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1178--1188",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453981",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dalvi:2008:KSE,
  author =       "Bhavana Bharat Dalvi and Meghana Kshirsagar and S.
                 Sudarshan",
  title =        "Keyword search on external memory data graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1189--1204",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453982",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koltsidas:2008:SHD,
  author =       "Ioannis Koltsidas and Heiko M{\"u}ller and Stratis D.
                 Viglas",
  title =        "Sorting hierarchical data in external memory for
                 archiving",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "1",
  pages =        "1205--1216",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1453856.1453983",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:36 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Metwally:2008:SSP,
  author =       "Ahmed Metwally and Fatih Emek{\c{c}}i and Divyakant
                 Agrawal and Amr {El Abbadi}",
  title =        "{SLEUTH}: {Single-pubLisher attack dEtection Using
                 correlaTion Hunting}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1217--1228",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454161",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Poess:2008:ECK,
  author =       "Meikel Poess and Raghunath Othayoth Nambiar",
  title =        "Energy cost, the key challenge of today's data
                 centers: a power consumption analysis of {TPC}-{C}
                 results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1229--1240",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454162",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Madhavan:2008:GDW,
  author =       "Jayant Madhavan and David Ko and Lucja Kot and Vignesh
                 Ganapathy and Alex Rasmussen and Alon Halevy",
  title =        "{Google}'s {Deep Web} crawl",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1241--1252",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454163",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Weis:2008:ISD,
  author =       "Melanie Weis and Felix Naumann and Ulrich Jehle and
                 Jens Lufter and Holger Schuster",
  title =        "Industry-scale duplicate detection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1253--1264",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454165",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaiken:2008:SEE,
  author =       "Ronnie Chaiken and Bob Jenkins and Per-{\AA}ke Larson
                 and Bill Ramsey and Darren Shakib and Simon Weaver and
                 Jingren Zhou",
  title =        "{SCOPE}: easy and efficient parallel processing of
                 massive data sets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1265--1276",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454166",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cooper:2008:PYH,
  author =       "Brian F. Cooper and Raghu Ramakrishnan and Utkarsh
                 Srivastava and Adam Silberstein and Philip Bohannon and
                 Hans-Arno Jacobsen and Nick Puz and Daniel Weaver and
                 Ramana Yerneni",
  title =        "{PNUTS}: {Yahoo!}'s hosted data serving platform",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1277--1288",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454167",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Acharya:2008:RSF,
  author =       "Srini Acharya and Peter Carlin and Cesar
                 Galindo-Legaria and Krzysztof Kozielczyk and Pawel
                 Terlecki and Peter Zabback",
  title =        "Relational support for flexible schema scenarios",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1289--1300",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454169",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mukherjee:2008:OSS,
  author =       "Niloy Mukherjee and Bharath Aleti and Amit Ganesh and
                 Krishna Kunchithapadam and Scott Lynn and Sujatha
                 Muthulingam and Kam Shergill and Shaoyu Wang and Wei
                 Zhang",
  title =        "{Oracle SecureFiles System}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1301--1312",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454170",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chhugani:2008:EIS,
  author =       "Jatin Chhugani and Anthony D. Nguyen and Victor W. Lee
                 and William Macy and Mostafa Hagog and Yen-Kuang Chen
                 and Akram Baransi and Sanjeev Kumar and Pradeep Dubey",
  title =        "Efficient implementation of sorting on multi-core
                 {SIMD CPU} architecture",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1313--1324",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454171",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dey:2008:EAQ,
  author =       "Atreyee Dey and Sourjya Bhaumik and Harish D. and
                 Jayant R. Haritsa",
  title =        "Efficiently approximating query optimizer plan
                 diagrams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1325--1336",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454173",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Slezak:2008:BAD,
  author =       "Dominik {\'S}l{\k{e}}zak and Jakub Wr{\'o}blewski and
                 Victoria Eastwood and Piotr Synak",
  title =        "{Brighthouse}: an analytic data warehouse for ad-hoc
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1337--1345",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454174",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ziauddin:2008:OPC,
  author =       "Mohamed Ziauddin and Dinesh Das and Hong Su and Yali
                 Zhu and Khaled Yagoub",
  title =        "Optimizer plan change management: improved stability
                 and performance in {Oracle} 11g",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1346--1355",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454175",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2008:TPX,
  author =       "Zhen Hua Liu and Sivasankaran Chandrasekar and Thomas
                 Baby and Hui J. Chang",
  title =        "Towards a physical {XML} independent {XQuery\slash
                 SQL\slash XML} engine",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1356--1367",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454177",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2008:CQP,
  author =       "Allison W. Lee and Mohamed Zait",
  title =        "Closing the query processing loop in {Oracle 11g}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1368--1378",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454178",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jain:2008:TSS,
  author =       "Namit Jain and Shailendra Mishra and Anand Srinivasan
                 and Johannes Gehrke and Jennifer Widom and Hari
                 Balakrishnan and U{\u{g}}ur {\c{C}}etintemel and Mitch
                 Cherniack and Richard Tibbetts and Stan Zdonik",
  title =        "Towards a streaming {SQL} standard",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1379--1390",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454179",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Huang:2008:ESG,
  author =       "Yu Huang and Ziyang Liu and Yi Chen",
  title =        "{eXtract}: a snippet generation system for {XML}
                 search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1392--1395",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454181",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Terwilliger:2008:LIQ,
  author =       "James F. Terwilliger and Sergey Melnik and Philip A.
                 Bernstein",
  title =        "Language-integrated querying of {XML} data in {SQL}
                 server",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1396--1399",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454182",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mathis:2008:XXC,
  author =       "Christian Mathis and Andreas M. Weiner and Theo
                 H{\"a}rder and Caesar Ralf Franz Hoppen",
  title =        "{XTCcmp}: {XQuery} compilation on {XTC}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1400--1403",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454183",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tian:2008:PGG,
  author =       "Yuanyuan Tian and Jignesh M. Patel and Viji Nair and
                 Sebastian Martini and Matthias Kretzler",
  title =        "{Periscope\slash GQ}: a graph querying toolkit",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1404--1407",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454184",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Balmin:2008:SSS,
  author =       "Andrey Balmin and Latha Colby and Emiran Curtmola and
                 Quanzhong Li and Fatma {\"O}zcan and Sharath Srinivas
                 and Zografoula Vagena",
  title =        "{SEDA}: a system for search, exploration, discovery,
                 and analysis of {XML Data}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1408--1411",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454185",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Motahari:2008:PSD,
  author =       "Hamid Motahari and Boualem Benatallah and Regis
                 Saint-Paul and Fabio Casati and Periklis Andritsos",
  title =        "Process spaceship: discovering and exploring process
                 views from event logs in data spaces",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1412--1415",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454186",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lupu:2008:PPP,
  author =       "Mihai Lupu and Y. C. Tay",
  title =        "{P} 3 {N}: profiling the potential of a peer-based
                 data management system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1416--1419",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454188",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tlili:2008:PLT,
  author =       "Mounir Tlili and W. Kokou Dedzoe and Esther Pacitti
                 and Patrick Valduriez and Reza Akbarinia and Pascal
                 Molli and G{\'e}r{\^o}me Canals and St{\'e}phane
                 Lauri{\`e}re",
  title =        "{P2P} logging and timestamping for reconciliation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1420--1423",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454189",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Luu:2008:ASP,
  author =       "Toan Luu and Gleb Skobeltsyn and Fabius Klemm and
                 Maroje Puh and Ivana Podnar Zarko and Martin Rajman and
                 Karl Aberer",
  title =        "{AlvisP2P}: scalable peer-to-peer text retrieval in a
                 structured {P2P} network",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1424--1427",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454190",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abiteboul:2008:WEP,
  author =       "S. Abiteboul and T. Allard and P. Chatalic and G.
                 Gardarin and A. Ghitescu and F. Goasdou{\'e} and I.
                 Manolescu and B. Nguyen and M. Ouazara and A. Somani
                 and N. Travers and G. Vasile and S. Zoupanos",
  title =        "{WebContent}: efficient {P2P Warehousing} of {Web}
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1428--1431",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454191",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jurczyk:2008:DED,
  author =       "Pawel Jurczyk and Li Xiong",
  title =        "{DObjects}: enabling distributed data services for
                 metacomputing platforms",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1432--1435",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454192",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shao:2008:ETR,
  author =       "Qihong Shao and Yi Chen and Shu Tao and Xifeng Yan and
                 Nikos Anerousis",
  title =        "{EasyTicket}: a ticket routing recommendation engine
                 for enterprise problem resolution",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1436--1439",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454193",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Duda:2008:ACI,
  author =       "Cristian Duda and Gianni Frey and Donald Kossmann and
                 Chong Zhou",
  title =        "{AJAXSearch}: crawling, indexing and searching {Web
                 2.0} applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1440--1443",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454195",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2008:MSH,
  author =       "Kun Liu and Evimaria Terzi and Tyrone Grandison",
  title =        "{ManyAspects}: a system for highlighting diverse
                 concepts in documents",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1444--1447",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454196",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Curtmola:2008:XDC,
  author =       "Emiran Curtmola and Alin Deutsch and Dionysios
                 Logothetis and K. K. Ramakrishnan and Divesh Srivastava
                 and Kenneth Yocum",
  title =        "{XTreeNet}: democratic community search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1448--1451",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454197",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2008:EVK,
  author =       "Guoliang Li and Jianhua Feng and Jianyong Wang and
                 Lizhu Zhou",
  title =        "An effective and versatile keyword search engine on
                 heterogeneous data sources",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1452--1455",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454198",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Baid:2008:DME,
  author =       "Akanksha Baid and Andrey Balmin and Heasoo Hwang and
                 Erik Nijkamp and Jun Rao and Berthold Reinwald and
                 Alkis Simitsis and Yannis Sismanis and Frank van Ham",
  title =        "{DBPubs}: multidimensional exploration of database
                 publications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1456--1459",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454199",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2008:SDQ,
  author =       "Wenfei Fan and Floris Geerts and Xibei Jia",
  title =        "{Semandaq}: a data quality system based on conditional
                 functional dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1460--1463",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454200",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Katsis:2008:RTI,
  author =       "Yannis Katsis and Alin Deutsch and Yannis
                 Papakonstantinou and Keliang Zhao",
  title =        "{RIDE}: a tool for interactive source registration in
                 community-oriented information integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1464--1467",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454202",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alexe:2008:CEM,
  author =       "Bogdan Alexe and Wang-Chiew Tan and Yannis
                 Velegrakis",
  title =        "Comparing and evaluating mapping systems with
                 {STBenchmark}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1468--1471",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454203",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Logothetis:2008:AHD,
  author =       "Dionysios Logothetis and Kenneth Yocum",
  title =        "Ad-hoc data processing in the cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1472--1475",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454204",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Weigel:2008:LSC,
  author =       "Felix Weigel and Biswanath Panda and Mirek Riedewald
                 and Johannes Gehrke and Manuel Calimlim",
  title =        "Large-scale collaborative analysis and extraction of
                 {Web} data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1476--1479",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454205",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Crecelius:2008:MSS,
  author =       "Tom Crecelius and Mouna Kacimi and Sebastian Michel
                 and Thomas Neumann and Josiane Xavier Parreira and Ralf
                 Schenkel and Gerhard Weikum",
  title =        "Making {SENSE}: socially enhanced search and
                 exploration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1480--1483",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454206",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lu:2008:ASD,
  author =       "Wentian Lu and Gerome Miklau",
  title =        "{AuditGuard}: a system for database auditing under
                 retention restrictions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1484--1487",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454207",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hu:2008:QVQ,
  author =       "Ling Hu and Kenneth A. Ross and Yuan-Chi Chang and
                 Christian A. Lang and Donghui Zhang",
  title =        "{QueryScope}: visualizing queries for repeatable
                 database tuning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1488--1491",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454209",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hose:2008:WIT,
  author =       "Katja Hose and Daniel Klan and Matthias Marx and
                 Kai-Uwe Sattler",
  title =        "When is it time to rethink the aggregate configuration
                 of your {OLAP} server?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1492--1495",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454210",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kallman:2008:HSH,
  author =       "Robert Kallman and Hideaki Kimura and Jonathan Natkins
                 and Andrew Pavlo and Alexander Rasin and Stanley Zdonik
                 and Evan P. C. Jones and Samuel Madden and Michael
                 Stonebraker and Yang Zhang and John Hugg and Daniel J.
                 Abadi",
  title =        "{H-store}: a high-performance, distributed main memory
                 transaction processing system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1496--1499",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454211",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Perlman:2008:OIN,
  author =       "Eric Perlman and Randal Burns and Michael Kazhdan",
  title =        "Organizing and indexing non-convex regions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1500--1503",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454212",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Paquet:2008:CME,
  author =       "Eric Paquet and Herna L. Viktor",
  title =        "{Capri\slash MR}: exploring protein databases from a
                 structural and physicochemical point of view",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1504--1507",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454213",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guo:2008:CMM,
  author =       "Fan Guo and Lei Li and Christos Faloutsos and Eric P.
                 Xing",
  title =        "{C-DEM}: a multi-modal query system for {Drosophila
                 Embryo} databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1508--1511",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454214",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Milo:2008:QMD,
  author =       "Tova Milo and Daniel Deutch",
  title =        "Querying and monitoring distributed business
                 processes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1512--1515",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454216",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Franklin:2008:FTD,
  author =       "Michael Franklin and Alon Halevy and David Maier",
  title =        "A first tutorial on dataspaces",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1516--1517",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454217",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Franconi:2008:ODM,
  author =       "Enrico Franconi",
  title =        "Ontologies and databases: myths and challenges",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1518--1519",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454218",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Balazinska:2008:SAP,
  author =       "Magdalena Balazinska and Christopher R{\'e} and Dan
                 Suciu",
  title =        "Systems aspects of probabilistic data management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1520--1521",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454219",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2008:RIC,
  author =       "Wenfei Fan and Floris Geerts and Xibei Jia",
  title =        "A revival of integrity constraints for data cleaning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1522--1523",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454220",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Moro:2008:XSS,
  author =       "Mirella M. Moro and Zografoula Vagena and Vassilis J.
                 Tsotras",
  title =        "{XML Structural Summaries}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1524--1525",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454221",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sharaf:2008:SCQ,
  author =       "Mohamed A. Sharaf and Alexandros Labrinidis and Panos
                 K. Chrysanthis",
  title =        "Scheduling continuous queries in data stream
                 management systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1526--1527",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454222",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kriegel:2008:DCM,
  author =       "Hans-Peter Kriegel and Peer Kr{\"o}ger and Arthur
                 Zimek",
  title =        "Detecting clusters in moderate-to-high dimensional
                 data: subspace clustering, pattern-based clustering,
                 and correlation clustering",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1528--1529",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454223",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cormode:2008:FFI,
  author =       "Graham Cormode and Marios Hadjieleftheriou",
  title =        "Finding frequent items in data streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1530--1541",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454225",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ding:2008:QMT,
  author =       "Hui Ding and Goce Trajcevski and Peter Scheuermann and
                 Xiaoyue Wang and Eamonn Keogh",
  title =        "Querying and mining of time series data: experimental
                 comparison of representations and distance measures",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1542--1552",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454226",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sidirourgos:2008:CSS,
  author =       "Lefteris Sidirourgos and Romulo Goncalves and Martin
                 Kersten and Niels Nes and Stefan Manegold",
  title =        "Column-store support for {RDF} data management: not
                 all swans are white",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1553--1563",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454227",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sans:2008:PBN,
  author =       "Virginie Sans and Dominique Laurent",
  title =        "Prefix based numbering schemes for {XML}: techniques,
                 applications and performances",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1564--1573",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454228",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2008:BEM,
  author =       "Su Chen and Christian S. Jensen and Dan Lin",
  title =        "A benchmark for evaluating moving object indexes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1574--1585",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454229",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dittrich:2008:DRM,
  author =       "Jens Dittrich and Lukas Blunschi and Marcos Antonio
                 Vaz Salles",
  title =        "Dwarfs in the rearview mirror: how big are they
                 really?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1586--1597",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454230",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shao:2008:CTE,
  author =       "Jie Shao and Heng Tao Shen and Xiaofang Zhou",
  title =        "Challenges and techniques for effective and efficient
                 similarity search in large video databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1598--1603",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454232",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hopfgartner:2008:SIM,
  author =       "Frank Hopfgartner",
  title =        "Studying interaction methodologies in video
                 retrieval",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1604--1608",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454233",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lo:2008:MPR,
  author =       "David Lo and Siau-Cheng Khoo",
  title =        "Mining patterns and rules for software specification
                 discovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1609--1616",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454234",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Biveinis:2008:TEM,
  author =       "Laurynas Biveinis and Simonas Saltenis",
  title =        "Towards efficient main-memory use for optimum tree
                 index update",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1617--1622",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454236",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Holupirek:2008:IFT,
  author =       "Alexander Holupirek and Marc H. Scholl",
  title =        "Implementing filesystems by tree-aware {DBMSs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1623--1630",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454237",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Avanes:2008:AWS,
  author =       "Artin Avanes and Johann-Christoph Freytag",
  title =        "Adaptive workflow scheduling under resource allocation
                 constraints and network dynamics",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1631--1637",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454238",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zerr:2008:PPD,
  author =       "Sergej Zerr and Wolfgang Nejdl",
  title =        "Privacy preserving document indexing infrastructure
                 for a distributed environment",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1638--1643",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454240",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Miao:2008:GTG,
  author =       "Jiajia Miao",
  title =        "{GS-TMS}: a global stream-based threat monitor
                 system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1644--1651",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454241",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kharlamov:2008:III,
  author =       "Evgeny Kharlamov and Werner Nutt",
  title =        "Incompleteness in information integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1652--1658",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454242",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deutch:2008:QWB,
  author =       "Daniel Deutch and Tova Milo",
  title =        "Querying {Web}-based applications under models of
                 uncertainty",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1659--1665",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454244",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Silvasti:2008:XDF,
  author =       "Panu Silvasti and Seppo Sippu and Eljas
                 Soisalon-Soininen",
  title =        "{XML}-document-filtering automaton",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1666--1671",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454245",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Scholl:2008:CDD,
  author =       "Tobias Scholl and Alfons Kemper",
  title =        "Community-driven data grids",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "1",
  number =       "2",
  pages =        "1672--1677",
  month =        aug,
  year =         "2008",
  CODEN =        "????",
  DOI =          "http://dx.doi.org/10.1145/1454159.1454246",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:44 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gatterbauer:2009:BIA,
  author =       "Wolfgang Gatterbauer and Magdalena Balazinska and
                 Nodira Khoussainova and Dan Suciu",
  title =        "Believe it or not: adding belief annotations to
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1--12",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2009:SSB,
  author =       "Zhenjie Zhang and Beng Chin Ooi and Srinivasan
                 Parthasarathy and Anthony K. H. Tung",
  title =        "Similarity search on {Bregman} divergence: towards
                 non-metric indexing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "13--24",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zeng:2009:CSA,
  author =       "Zhiping Zeng and Anthony K. H. Tung and Jianyong Wang
                 and Jianhua Feng and Lizhu Zhou",
  title =        "Comparing stars: on approximating graph edit
                 distance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "25--36",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Whang:2009:IBE,
  author =       "Steven Euijong Whang and Hector Garcia-Molina and Chad
                 Brower and Jayavel Shanmugasundaram and Sergei
                 Vassilvitskii and Erik Vee and Ramana Yerneni",
  title =        "Indexing {Boolean} expressions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "37--48",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhou:2009:SDS,
  author =       "Yongluan Zhou and Ali Salehi and Karl Aberer",
  title =        "Scalable delivery of stream query result",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "49--60",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Benedikt:2009:SBI,
  author =       "Michael Benedikt and James Cheney",
  title =        "Schema-based independence analysis for {XML} updates",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "61--72",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nehme:2009:TSD,
  author =       "Rimma V. Nehme and Elke A. Rundensteiner and Elisa
                 Bertino",
  title =        "Tagging stream data for rich real-time services",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "73--84",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sarma:2009:RMP,
  author =       "Atish Das Sarma and Ashwin Lall and Danupon Nanongkai
                 and Jun Xu",
  title =        "Randomized multi-pass streaming skyline algorithms",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "85--96",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Reeves:2009:MMT,
  author =       "Galen Reeves and Jie Liu and Suman Nath and Feng
                 Zhao",
  title =        "Managing massive time series streams with multi-scale
                 compressed trickles",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "97--108",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2009:PAM,
  author =       "Tianyi Wu and Dong Xin and Qiaozhu Mei and Jiawei
                 Han",
  title =        "Promotion analysis in multi-dimensional space",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "109--120",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sarkas:2009:MDK,
  author =       "Nikos Sarkas and Nilesh Bansal and Gautam Das and Nick
                 Koudas",
  title =        "Measure-driven keyword-query expansion",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "121--132",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2009:UTD,
  author =       "Bin Liu and H. V. Jagadish",
  title =        "Using trees to depict a forest",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "133--144",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Elmeleegy:2009:OPW,
  author =       "Hazem Elmeleegy and Ahmed K. Elmagarmid and Emmanuel
                 Cecchet and Walid G. Aref and Willy Zwaenepoel",
  title =        "Online piece-wise linear approximation of numerical
                 streams with precision guarantees",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "145--156",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Stern:2009:WTE,
  author =       "Mirco Stern and Erik Buchmann and Klemens B{\"o}hm",
  title =        "A wavelet transform for efficient consolidation of
                 sensor relations with quality guarantees",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "157--168",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yu:2009:EAQ,
  author =       "Liu Yu and Jianzhong Li and Hong Gao and Xiaolin
                 Fang",
  title =        "Enabling $\epsilon$-approximate querying in sensor
                 networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "169--180",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nandi:2009:HUS,
  author =       "Arnab Nandi and Philip A. Bernstein",
  title =        "{HAMSTER}: using search clicklogs for schema and
                 taxonomy matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "181--192",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kot:2009:CUE,
  author =       "Lucja Kot and Christoph Koch",
  title =        "Cooperative update exchange in the {Youtopia} system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "193--204",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Papapetrou:2009:RBA,
  author =       "Panagiotis Papapetrou and Vassilis Athitsos and George
                 Kollios and Dimitrios Gunopulos",
  title =        "Reference-based alignment in large sequence
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "205--216",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Das:2009:TCM,
  author =       "Sudipto Das and Shyam Antony and Divyakant Agrawal and
                 Amr {El Abbadi}",
  title =        "Thread cooperation in multicore architectures for
                 frequency counting over multiple data streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "217--228",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mueller:2009:SWQ,
  author =       "Rene Mueller and Jens Teubner and Gustavo Alonso",
  title =        "Streams on wires: a query compiler for {FPGAs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "229--240",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chandramouli:2009:FPD,
  author =       "Badrish Chandramouli and Jonathan Goldstein and David
                 Maier",
  title =        "On-the-fly progress detection in iterative stream
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "241--252",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kraska:2009:CRC,
  author =       "Tim Kraska and Martin Hentschel and Gustavo Alonso and
                 Donald Kossmann",
  title =        "Consistency rationing in the cloud: pay only when it
                 matters",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "253--264",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lomet:2009:LKR,
  author =       "David Lomet and Mohamed F. Mokbel",
  title =        "Locking key ranges with unbundled transaction
                 services",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "265--276",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Candea:2009:SPJ,
  author =       "George Candea and Neoklis Polyzotis and Radek
                 Vingralek",
  title =        "A scalable, predictable join operator for highly
                 concurrent data warehouses",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "277--288",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gupta:2009:ATA,
  author =       "Rahul Gupta and Sunita Sarawagi",
  title =        "Answering table augmentation queries from unstructured
                 lists on the {Web}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "289--300",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cautis:2009:ERX,
  author =       "Bogdan Cautis and Alin Deutsch and Nicola Onose and
                 Vasilis Vassalos",
  title =        "Efficient rewriting of {XPath} queries using {Query
                 Set Specifications}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "301--312",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2009:SSR,
  author =       "Ziyang Liu and Peng Sun and Yi Chen",
  title =        "Structured search result differentiation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "313--324",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dragut:2009:HAM,
  author =       "Eduard C. Dragut and Thomas Kabisch and Clement Yu and
                 Ulf Leser",
  title =        "A hierarchical approach to model {Web} query
                 interfaces for {Web} source integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "325--336",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cong:2009:ERT,
  author =       "Gao Cong and Christian S. Jensen and Dingming Wu",
  title =        "Efficient retrieval of the top-$k$ most relevant
                 spatial {Web} objects",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "337--348",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dragut:2009:SWR,
  author =       "Eduard Dragut and Fang Fang and Prasad Sistla and
                 Clement Yu and Weiyi Meng",
  title =        "Stop word and related problems in {Web} interface
                 integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "349--360",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agrawal:2009:LAT,
  author =       "Devesh Agrawal and Deepak Ganesan and Ramesh Sitaraman
                 and Yanlei Diao and Shashi Singh",
  title =        "Lazy-Adaptive {Tree}: an optimized index structure for
                 flash devices",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "361--372",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2009:MDM,
  author =       "Rubao Lee and Xiaoning Ding and Feng Chen and Qingda
                 Lu and Xiaodong Zhang",
  title =        "{MCC-DB}: minimizing cache conflicts in multi-core
                 processors for databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "373--384",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Willhalm:2009:SSU,
  author =       "Thomas Willhalm and Nicolae Popovici and Yazan Boshmaf
                 and Hasso Plattner and Alexander Zeier and Jan
                 Schaffner",
  title =        "{SIMD-scan}: ultra fast in-memory table scan using
                 on-chip vector processing units",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "385--394",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaudhuri:2009:MDC,
  author =       "Surajit Chaudhuri and Venkatesh Ganti and Dong Xin",
  title =        "Mining document collections to facilitate accurate
                 approximate entity matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "395--406",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2009:RAR,
  author =       "Wenfei Fan and Xibei Jia and Jianzhong Li and Shuai
                 Ma",
  title =        "Reasoning about record matching rules",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "407--418",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dobra:2009:TCE,
  author =       "Alin Dobra and Chris Jermaine and Florin Rusu and Fei
                 Xu",
  title =        "Turbo-charging estimate convergence in {DBO}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "419--430",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cohen:2009:CSA,
  author =       "Edith Cohen and Nick Duffield and Haim Kaplan and
                 Carsten Lund and Mikkel Thorup",
  title =        "Composable, scalable, and accurate weight
                 summarization of unaggregated data sets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "431--442",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2009:DOA,
  author =       "Sai Wu and Shouxu Jiang and Beng Chin Ooi and Kian-Lee
                 Tan",
  title =        "Distributed online aggregations",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "443--454",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koloniari:2009:RBC,
  author =       "Georgia Koloniari and Evaggelia Pitoura",
  title =        "A recall-based cluster formation game in peer-to-peer
                 systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "455--466",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fekete:2009:QIA,
  author =       "Alan Fekete and Shirley N. Goldrei and Jorge P{\'e}rez
                 Asenjo",
  title =        "Quantifying isolation anomalies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "467--478",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Johnson:2009:IOS,
  author =       "Ryan Johnson and Ippokratis Pandis and Anastasia
                 Ailamaki",
  title =        "Improving {OLTP} scalability using speculative lock
                 inheritance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "479--489",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sears:2009:SBR,
  author =       "Russell Sears and Eric Brewer",
  title =        "Segment-based recovery: write-ahead logging
                 revisited",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "490--501",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2009:UAR,
  author =       "Jian Li and Barna Saha and Amol Deshpande",
  title =        "A unified approach to ranking in probabilistic
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "502--513",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Arasu:2009:LST,
  author =       "Arvind Arasu and Surajit Chaudhuri and Raghav
                 Kaushik",
  title =        "Learning string transformations from examples",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "514--525",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cormode:2009:PHP,
  author =       "Graham Cormode and Antonios Deligiannakis and Minos
                 Garofalakis and Andrew McGregor",
  title =        "Probabilistic histograms for probabilistic data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "526--537",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Greenshpan:2009:AM,
  author =       "Ohad Greenshpan and Tova Milo and Neoklis Polyzotis",
  title =        "Autocompletion for mashups",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "538--549",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dong:2009:ICD,
  author =       "Xin Luna Dong and Laure Berti-Equille and Divesh
                 Srivastava",
  title =        "Integrating conflicting data: the role of source
                 dependence",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "550--561",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dong:2009:TDC,
  author =       "Xin Luna Dong and Laure Berti-Equille and Divesh
                 Srivastava",
  title =        "Truth discovery and copying detection in a dynamic
                 world",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "562--573",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Golab:2009:SD,
  author =       "Lukasz Golab and Howard Karloff and Flip Korn and
                 Avishek Saha and Divesh Srivastava",
  title =        "Sequential dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "574--585",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Denev:2009:SFQ,
  author =       "Dimitar Denev and Arturas Mazeika and Marc Spaniol and
                 Gerhard Weikum",
  title =        "{SHARC}: framework for quality-conscious {Web}
                 archiving",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "586--597",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Beskales:2009:MQP,
  author =       "George Beskales and Mohamed A. Soliman and Ihab F.
                 Ilyas and Shai Ben-David",
  title =        "Modeling and querying possible repairs in duplicate
                 detection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "598--609",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mindolin:2009:DRI,
  author =       "Denis Mindolin and Jan Chomicki",
  title =        "Discovering relative importance of skyline
                 attributes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "610--621",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kim:2009:PDB,
  author =       "Min-Soo Kim and Jiawei Han",
  title =        "A particle-and-density based evolutionary clustering
                 method for dynamic networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "622--633",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2009:SRD,
  author =       "Xiaoyan Yang and Cecilia M. Procopiuc and Divesh
                 Srivastava",
  title =        "Summarizing relational databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "634--645",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cohen:2009:CWS,
  author =       "Edith Cohen and Haim Kaplan and Subhabrata Sen",
  title =        "Coordinated weighted sampling for estimating
                 aggregates over multiple weight assignments",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "646--657",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2009:PLB,
  author =       "Hongrae Lee and Raymond T. Ng and Kyuseok Shim",
  title =        "Power-law based estimation of set similarity join
                 size",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "658--669",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Karras:2009:OSL,
  author =       "Panagiotis Karras",
  title =        "Optimality and scalability in lattice histogram
                 construction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "670--681",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Vigfusson:2009:APD,
  author =       "Ymir Vigfusson and Adam Silberstein and Brian F.
                 Cooper and Rodrigo Fonseca",
  title =        "Adaptively parallelizing distributed range queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "682--693",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tatikonda:2009:MTS,
  author =       "Shirish Tatikonda and Srinivasan Parthasarathy",
  title =        "Mining tree-structured data on multicore systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "694--705",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Unterbrunner:2009:PPU,
  author =       "P. Unterbrunner and G. Giannikis and G. Alonso and D.
                 Fauser and D. Kossmann",
  title =        "Predictable performance for unpredictable workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "706--717",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhou:2009:GCB,
  author =       "Yang Zhou and Hong Cheng and Jeffrey Xu Yu",
  title =        "Graph clustering based on structural\slash attribute
                 similarities",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "718--729",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{AlHasan:2009:OSS,
  author =       "Mohammad {Al Hasan} and Mohammed J. Zaki",
  title =        "Output space sampling for graph patterns",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "730--741",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2009:MGP,
  author =       "Chen Chen and Cindy X. Lin and Matt Fredrikson and
                 Mihai Christodorescu and Xifeng Yan and Jiawei Han",
  title =        "Mining graph patterns efficiently via randomized
                 summaries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "742--753",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Amer-Yahia:2009:GRS,
  author =       "Sihem Amer-Yahia and Senjuti Basu Roy and Ashish
                 Chawlat and Gautam Das and Cong Yu",
  title =        "Group recommendation: semantics and efficiency",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "754--765",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bhagat:2009:CBG,
  author =       "Smriti Bhagat and Graham Cormode and Balachander
                 Krishnamurthy and Divesh Srivastava",
  title =        "Class-based graph anonymization for social network
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "766--777",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sarkas:2009:ISS,
  author =       "Nikos Sarkas and Gautam Das and Nick Koudas",
  title =        "Improved search for socially annotated data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "778--789",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Machanavajjhala:2009:DPA,
  author =       "Ashwin Machanavajjhala and Johannes Gehrke and
                 Michaela G{\"o}tz",
  title =        "Data publishing against realistic adversaries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "790--801",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pang:2009:SVO,
  author =       "HweeHwa Pang and Jilian Zhang and Kyriakos
                 Mouratidis",
  title =        "Scalable verification for outsourced dynamic
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "802--813",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xiao:2009:ORP,
  author =       "Xiaokui Xiao and Yufei Tao and Minghua Chen",
  title =        "Optimal random perturbation at multiple privacy
                 levels",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "814--825",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Assent:2009:ADE,
  author =       "Ira Assent and Marc Wichterich and Ralph Krieger and
                 Hardy Kremer and Thomas Seidl",
  title =        "Anticipatory {DTW} for efficient similarity search in
                 time series databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "826--837",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tsirogiannis:2009:IPL,
  author =       "Dimitris Tsirogiannis and Sudipto Guha and Nick
                 Koudas",
  title =        "Improving the performance of list intersection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "838--849",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kaushik:2009:CHP,
  author =       "Raghav Kaushik and Dan Suciu",
  title =        "Consistent histograms in the presence of distinct
                 value counts",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "850--861",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Aggarwal:2009:GCI,
  author =       "Charu Aggarwal and Yan Xie and Philip S. Yu",
  title =        "{GConnect}: a connectivity index for massive
                 disk-resident graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "862--873",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2009:SES,
  author =       "Di Yang and Elke A. Rundensteiner and Matthew O.
                 Ward",
  title =        "A shared execution strategy for multiple pattern
                 mining requests over streaming data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "874--885",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zou:2009:DJP,
  author =       "Lei Zou and Lei Chen and M. Tamer {\"O}zsu",
  title =        "Distance-join: pattern match query in a large graph
                 database",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "886--897",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wan:2009:CCP,
  author =       "Qian Wan and Raymond Chi-Wing Wong and Ihab F. Ilyas
                 and M. Tamer {\"O}zsu and Yu Peng",
  title =        "Creating competitive products",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "898--909",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mueller:2009:DPF,
  author =       "Rene Mueller and Jens Teubner and Gustavo Alonso",
  title =        "Data processing on {FPGAs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "910--921",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abouzeid:2009:HAH,
  author =       "Azza Abouzeid and Kamil Bajda-Pawlikowski and Daniel
                 Abadi and Avi Silberschatz and Alexander Rasin",
  title =        "{HadoopDB}: an architectural hybrid of {MapReduce} and
                 {DBMS} technologies for analytical workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "922--933",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{He:2009:ASV,
  author =       "Yeye He and Jeffrey F. Naughton",
  title =        "Anonymization of set-valued data via top-down, local
                 generalization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "934--945",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zou:2009:AGF,
  author =       "Lei Zou and Lei Chen and M. Tamer {\"O}zsu",
  title =        "$k$-automorphism: a general framework for privacy
                 preserving network publication",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "946--957",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koudas:2009:DBM,
  author =       "Nick Koudas and Divesh Srivastava and Ting Yu and Qing
                 Zhang",
  title =        "Distribution based microdata anonymization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "958--969",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Meier:2009:CTB,
  author =       "Michael Meier and Michael Schmidt and Georg Lausen",
  title =        "On chase termination beyond stratification",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "970--981",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Moerkotte:2009:PBP,
  author =       "Guido Moerkotte and Thomas Neumann and Gabriele
                 Steidl",
  title =        "Preventing bad plans by bounding the impact of
                 cardinality estimation errors",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "982--993",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaudhuri:2009:ECQ,
  author =       "Surajit Chaudhuri and Vivek Narasayya and Ravi
                 Ramamurthy",
  title =        "Exact cardinality query optimization for optimizer
                 testing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "994--1005",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{tenCate:2009:LSM,
  author =       "Balder ten Cate and Laura Chiticariu and Phokion
                 Kolaitis and Wang-Chiew Tan",
  title =        "Laconic schema mappings: computing the core with {SQL}
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1006--1017",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Arenas:2009:ISM,
  author =       "Marcelo Arenas and Jorge P{\'e}rez and Juan Reutter
                 and Cristian Riveros",
  title =        "Inverting schema mappings: bridging the gap between
                 theory and practice",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1018--1029",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Terwilliger:2009:FFF,
  author =       "James F. Terwilliger and Philip A. Bernstein and
                 Sergey Melnik",
  title =        "Full-fidelity flexible object-oriented {XML} access",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1030--1041",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2009:PAM,
  author =       "Ting Wang and Ling Liu",
  title =        "Privacy-aware mobile services over road networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1042--1053",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{U:2009:FAA,
  author =       "Leong Hou U. and Nikos Mamoulis and Kyriakos
                 Mouratidis",
  title =        "A fair assignment algorithm for multiple preference
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1054--1065",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mishima:2009:PED,
  author =       "Takeshi Mishima and Hiroshi Nakamura",
  title =        "Pangea: an eager database replication middleware
                 guaranteeing snapshot isolation without modification of
                 database servers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1066--1077",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Elmeleegy:2009:HRT,
  author =       "Hazem Elmeleegy and Jayant Madhavan and Alon Halevy",
  title =        "Harvesting relational tables from lists on the web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1078--1089",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cafarella:2009:DIR,
  author =       "Michael J. Cafarella and Alon Halevy and Nodira
                 Khoussainova",
  title =        "Data integration for the relational web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1090--1101",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gottlob:2009:NOS,
  author =       "Georg Gottlob and Reinhard Pichler and Vadim
                 Savenkov",
  title =        "Normalization and optimization of schema mappings",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1102--1113",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xing:2009:CMN,
  author =       "Songhua Xing and Cyrus Shahabi and Bei Pan",
  title =        "Continuous monitoring of nearest neighbors on land
                 surface",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1114--1125",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wong:2009:EMM,
  author =       "Raymond Chi-Wing Wong and M. Tamer {\"O}zsu and Philip
                 S. Yu and Ada Wai-Chee Fu and Lian Liu",
  title =        "Efficient method for maximizing bichromatic reverse
                 nearest neighbor",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1126--1137",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheema:2009:LUE,
  author =       "Muhammad Aamir Cheema and Xuemin Lin and Ying Zhang
                 and Wei Wang and Wenjie Zhang",
  title =        "Lazy updates: an efficient technique to continuously
                 monitoring reverse {kNN}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1138--1149",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2009:NMM,
  author =       "Ling Chen and Sourav S. Bhowmick and Wolfgang Nejdl",
  title =        "{NEAR-Miner}: mining evolution associations of {Web}
                 site directories for efficient maintenance of {Web}
                 archives",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1150--1161",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wong:2009:AEO,
  author =       "W. K. Wong and David W. Cheung and Edward Hung and Ben
                 Kao and Nikos Mamoulis",
  title =        "An audit environment for outsourcing of frequent
                 itemset mining",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1162--1173",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mozafari:2009:PNB,
  author =       "Barzan Mozafari and Carlo Zaniolo",
  title =        "Publishing naive {Bayesian} classifiers: privacy
                 without accuracy loss",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1174--1185",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tzoumas:2009:WAI,
  author =       "Kostas Tzoumas and Man Lung Yiu and Christian S.
                 Jensen",
  title =        "Workload-aware indexing of continuously moving
                 objects",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1186--1197",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2009:EIU,
  author =       "Meihui Zhang and Su Chen and Christian S. Jensen and
                 Beng Chin Ooi and Zhenjie Zhang",
  title =        "Effectively indexing uncertain moving objects for
                 predictive queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1198--1209",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sankaranarayanan:2009:POS,
  author =       "Jagan Sankaranarayanan and Hanan Samet and Houman
                 Alborzi",
  title =        "Path oracles for spatial networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1210--1221",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kimura:2009:CMC,
  author =       "Hideaki Kimura and George Huo and Alexander Rasin and
                 Samuel Madden and Stanley B. Zdonik",
  title =        "Correlation maps: a compressed access method for
                 exploiting soft functional dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1222--1233",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Schnaitter:2009:IIP,
  author =       "Karl Schnaitter and Neoklis Polyzotis and Lise
                 Getoor",
  title =        "Index interactions in physical design tuning:
                 modeling, analysis, and applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1234--1245",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Duan:2009:TDC,
  author =       "Songyun Duan and Vamsidhar Thummala and Shivnath
                 Babu",
  title =        "Tuning database configuration parameters with
                 {iTuned}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1246--1257",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Salles:2009:ECR,
  author =       "Marcos Vaz Salles and Tuan Cao and Benjamin Sowell and
                 Alan Demers and Johannes Gehrke and Christoph Koch and
                 Walker White",
  title =        "An evaluation of checkpoint recovery for massively
                 multiplayer online games",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1258--1269",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Muller:2009:ECS,
  author =       "Emmanuel M{\"u}ller and Stephan G{\"u}nnemann and Ira
                 Assent and Thomas Seidl",
  title =        "Evaluating clustering in subspace projections of high
                 dimensional data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1270--1281",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hassanzadeh:2009:FEC,
  author =       "Oktie Hassanzadeh and Fei Chiang and Hyun Chul Lee and
                 Ren{\'e}e J. Miller",
  title =        "Framework for evaluating clustering algorithms in
                 duplicate detection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "1",
  pages =        "1282--1293",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:50 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guo:2009:DMM,
  author =       "Hongfei Guo and Dan Jones and Jennifer Beckmann and
                 Praveen Seshadri",
  title =        "Declarative management in {Microsoft SQL} server",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1294--1305",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{El-Helw:2009:SRS,
  author =       "Amr El-Helw and Ihab F. Ilyas and Calisto Zuzarte",
  title =        "{StatAdvisor}: recommending statistical views",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1306--1317",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Canim:2009:OPA,
  author =       "Mustafa Canim and George A. Mihaila and Bishwaranjan
                 Bhattacharjee and Kenneth A. Ross and Christian A.
                 Lang",
  title =        "An object placement advisor for {DB2} using solid
                 state storage",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1318--1329",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bhide:2009:XXP,
  author =       "Manish Bhide and Manoj K. Agarwal and Amir Bar-Or and
                 Sriram Padmanabhan and Srinivas K. Mittapalli and
                 Girish Venkatachaliah",
  title =        "{XPEDIA}: {XML} processing for data integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1330--1341",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bamford:2009:XR,
  author =       "Roger Bamford and Vinayak Borkar and Matthias Brantner
                 and Peter M. Fischer and Daniela Florescu and David
                 Graf and Donald Kossmann and Tim Kraska and Dan Muresan
                 and Sorin Nasoi and Markos Zacharioudakis",
  title =        "{XQuery} reloaded",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1342--1353",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2009:BXS,
  author =       "Ning Zhang and Nipun Agarwal and Sivasankaran
                 Chandrasekar and Sam Idicula and Vijay Medi and Sabina
                 Petride and Balasubramanyam Sthanikam",
  title =        "Binary {XML} storage and query processing in {Oracle
                 11g}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1354--1365",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bellamkonda:2009:ESO,
  author =       "Srikanth Bellamkonda and Rafi Ahmed and Andrew
                 Witkowski and Angela Amor and Mohamed Zait and
                 Chun-Chieh Lin",
  title =        "Enhanced subquery optimizations in {Oracle}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1366--1377",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kim:2009:SVH,
  author =       "Changkyu Kim and Tim Kaldewey and Victor W. Lee and
                 Eric Sedlar and Anthony D. Nguyen and Nadathur Satish
                 and Jatin Chhugani and Andrea {Di Blas} and Pradeep
                 Dubey",
  title =        "Sort vs. {Hash} revisited: fast join implementation on
                 modern multi-core {CPUs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1378--1389",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xu:2009:EOJ,
  author =       "Yu Xu and Pekka Kostamaa",
  title =        "Efficient outer join data skew handling in parallel
                 {DBMS}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1390--1396",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Friedman:2009:SMP,
  author =       "Eric Friedman and Peter Pawlowski and John
                 Cieslewicz",
  title =        "{SQL\slash MapReduce}: a practical approach to
                 self-describing, polymorphic, and parallelizable
                 user-defined functions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1402--1413",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gates:2009:BHL,
  author =       "Alan F. Gates and Olga Natkovich and Shubham Chopra
                 and Pradeep Kamath and Shravan M. Narayanamurthy and
                 Christopher Olston and Benjamin Reed and Santhosh
                 Srinivasan and Utkarsh Srivastava",
  title =        "Building a high-level dataflow system on top of
                 {Map-Reduce}: the {Pig} experience",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1414--1425",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Panda:2009:PMP,
  author =       "Biswanath Panda and Joshua S. Herbach and Sugato Basu
                 and Roberto J. Bayardo",
  title =        "{PLANET}: massively parallel learning of tree
                 ensembles with {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1426--1437",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Legler:2009:RDT,
  author =       "Thomas Legler and Wolfgang Lehner and Jan Schaffner
                 and Jens Kr{\"u}ger",
  title =        "Robust and distributed top-n frequent-pattern mining
                 with {SAP BW} accelerator",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1438--1449",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dieu:2009:TUF,
  author =       "Nicolas Dieu and Adrian Dragusanu and Fran{\c{c}}oise
                 Fabret and Fran{\c{c}}ois Llirbat and Eric Simon",
  title =        "1,000 tables under the form",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1450--1461",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bhattacharjee:2009:EIC,
  author =       "Bishwaranjan Bhattacharjee and Lipyeow Lim and Timothy
                 Malkemus and George Mihaila and Kenneth Ross and
                 Sherman Lau and Cathy McArthur and Zoltan Toth and Reza
                 Sherkat",
  title =        "Efficient index compression in {DB2 LUW}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1462--1473",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lacroix:2009:SSW,
  author =       "Zo{\'e} Lacroix and Christophe Legendre and Spyro
                 Mousses",
  title =        "Storing scientific workflows in a database",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1474--1480",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cohen:2009:MSN,
  author =       "Jeffrey Cohen and Brian Dolan and Mark Dunlap and
                 Joseph M. Hellerstein and Caleb Welton",
  title =        "{MAD} skills: new analysis practices for big data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1481--1492",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ley:2009:DSL,
  author =       "Michael Ley",
  title =        "{DBLP}: some lessons learned",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1493--1500",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mukherjee:2009:OSP,
  author =       "Niloy Mukherjee and Amit Ganesh and Vinayagam
                 Djegaradjane and Sujatha Muthulingam and Wei Zhang and
                 Krishna Kunchithapadam and Scott Lynn and Bharath Aleti
                 and Kam Shergill and Shaoyu Wang",
  title =        "{Oracle SecureFiles}: prepared for the digital
                 deluge",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1501--1511",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Baumgartner:2009:SWD,
  author =       "Robert Baumgartner and Georg Gottlob and Marcus
                 Herzog",
  title =        "Scalable {Web} data extraction for online market
                 intelligence",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1512--1523",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rajaraman:2009:KHP,
  author =       "Anand Rajaraman",
  title =        "{Kosmix}: high-performance topic exploration using the
                 deep {Web}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1524--1529",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nehme:2009:QMM,
  author =       "Rimma V. Nehme and Karen E. Works and Elke A.
                 Rundensteiner and Elisa Bertino",
  title =        "Query mesh: multi-route query processing technology",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1530--1533",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cudre-Mauroux:2009:DSS,
  author =       "P. Cudre-Mauroux and H. Kimura and K.-T. Lim and J.
                 Rogers and R. Simakov and E. Soroush and P. Velikhov
                 and D. L. Wang and M. Balazinska and J. Becla and D.
                 DeWitt and B. Heath and D. Maier and S. Madden and J.
                 Patel and M. Stonebraker and S. Zdonik",
  title =        "A demonstration of {SciDB}: a science-oriented
                 {DBMS}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1534--1537",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2009:MMM,
  author =       "Kuien Liu and Ke Deng and Zhiming Ding and Mingshu Li
                 and Xiaofang Zhou",
  title =        "{MOIR\slash MT}: monitoring large-scale road network
                 traffic in real-time",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1538--1541",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Colle:2009:ODR,
  author =       "Romain Colle and Leonidas Galanis and Supiti
                 Buranawatanachoke and Stratos Papadomanolakis and Yujun
                 Wang",
  title =        "{Oracle Database Replay}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1542--1545",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Borisov:2009:DPD,
  author =       "Nedyalko Borisov and Shivnath Babu and Sandeep
                 Uttamchandani and Ramani Routray and Aameek Singh",
  title =        "{DIADS}: a problem diagnosis tool for databases and
                 storage area networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1546--1549",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Herschel:2009:ASA,
  author =       "Melanie Herschel and Mauricio A. Hern{\'a}ndez and
                 Wang-Chiew Tan",
  title =        "{Artemis}: a system for analyzing missing answers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1550--1553",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2009:DTS,
  author =       "Eugene Wu and Philippe Cudre-Mauroux and Samuel
                 Madden",
  title =        "Demonstration of the {TrajStore} system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1554--1557",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ali:2009:MCS,
  author =       "M. H. Ali and C. Gerea and B. S. Raman and B. Sezgin
                 and T. Tarnavski and T. Verona and P. Wang and P.
                 Zabback and A. Ananthanarayan and A. Kirilov and M. Lu
                 and A. Raizman and R. Krishnan and R. Schindlauer and
                 T. Grabs and S. Bjeletich and B. Chandramouli and J.
                 Goldstein and S. Bhat and Ying Li and V. {Di Nicola}
                 and X. Wang and David Maier and S. Grell and O. Nano
                 and I. Santos",
  title =        "{Microsoft CEP Server} and online behavioral
                 targeting",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1558--1561",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Krompass:2009:TMD,
  author =       "Stefan Krompass and Harumi Kuno and Janet L. Wiener
                 and Kevin Wilkinson and Umeshwar Dayal and Alfons
                 Kemper",
  title =        "A testbed for managing dynamic mixed workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1562--1565",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ahmad:2009:DSC,
  author =       "Yanif Ahmad and Christoph Koch",
  title =        "{DBToaster}: a {SQL} compiler for high-performance
                 delta processing in main-memory databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1566--1569",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Preda:2009:AAK,
  author =       "Nicoleta Preda and Fabian M. Suchanek and Gjergji
                 Kasneci and Thomas Neumann and Maya Ramanath and
                 Gerhard Weikum",
  title =        "{ANGIE}: active knowledge for interactive
                 exploration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1570--1573",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kopcke:2009:CEE,
  author =       "Hanna K{\"o}pcke and Andreas Thor and Erhard Rahm",
  title =        "Comparative evaluation of entity resolution approaches
                 with {FEVER}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1574--1577",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Brauer:2009:RDR,
  author =       "Falk Brauer and Wojciech Barczynski and Gregor
                 Hackenbroich and Marcus Schramm and Adrian Mocan and
                 Felix F{\"o}rster",
  title =        "{RankIE}: document retrieval on ranked entity graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1578--1581",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mecca:2009:CEM,
  author =       "Giansalvatore Mecca and Paolo Papotti and Salvatore
                 Raunich and Marcello Buoncristiano",
  title =        "Concise and expressive mappings with +Spicy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1582--1585",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cruz:2009:AEM,
  author =       "Isabel F. Cruz and Flavio Palandri Antonelli and
                 Cosmin Stroe",
  title =        "{AgreementMaker}: efficient matching for large
                 real-world schemas and ontologies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1586--1589",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hassanzadeh:2009:LQW,
  author =       "Oktie Hassanzadeh and Reynold Xin and Ren{\'e}e J.
                 Miller and Anastasios Kementsietsidis and Lipyeow Lim
                 and Min Wang",
  title =        "{Linkage Query Writer}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1590--1593",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2009:SEE,
  author =       "Xiaoyuan Wang and Xingzhi Sun and Feng Cao and Li Ma
                 and Nick Kanellos and Kang Zhang and Yue Pan and Yong
                 Yu",
  title =        "{SMDM}: enhancing enterprise-wide master data
                 management using semantic {Web} technologies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1594--1597",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gubanov:2009:IUR,
  author =       "Michael N. Gubanov and Lucian Popa and Howard Ho and
                 Hamid Pirahesh and Jeng-Yih Chang and Shr-Chang Chen",
  title =        "{IBM UFO} repository: object-oriented data
                 integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1598--1601",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2009:MSW,
  author =       "Huajun Chen and Bin Lu and Yuan Ni and Guotong Xie and
                 Chunying Zhou and Jinhua Mi and Zhaohui Wu",
  title =        "Mashup by surfing a {Web} of data {APIs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1602--1605",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pichler:2009:DDE,
  author =       "Reinhard Pichler and Vadim Savenkov",
  title =        "{DEMo}: data exchange modeling tool",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1606--1609",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Letchner:2009:LDW,
  author =       "Julie Letchner and Christopher R{\'e} and Magdalena
                 Balazinska and Matthai Philipose",
  title =        "Lahar demonstration: warehousing {Markovian} streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1610--1613",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sun:2009:WAC,
  author =       "Peng Sun and Ziyang Liu and Sivaramakrishnan Natarajan
                 and Susan B. Davidson and Yi Chen",
  title =        "{WOLVES}: achieving correct provenance analysis by
                 detecting and resolving unsound workflow views",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1614--1617",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dai:2009:TTI,
  author =       "Chenyun Dai and Gabriel Ghinita and Elisa Bertino and
                 Ji-Won Byun and Ninghui Li",
  title =        "{TIAMAT}: a tool for interactive analysis of microdata
                 anonymization techniques",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1618--1621",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yu:2009:IIN,
  author =       "Yintao Yu and Cindy X. Lin and Yizhou Sun and Chen
                 Chen and Jiawei Han and Binbin Liao and Tianyi Wu and
                 ChengXiang Zhai and Duo Zhang and Bo Zhao",
  title =        "{iNextCube}: information network-enhanced text cube",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1622--1625",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Thusoo:2009:HWS,
  author =       "Ashish Thusoo and Joydeep Sen Sarma and Namit Jain and
                 Zheng Shao and Prasad Chakka and Suresh Anthony and Hao
                 Liu and Pete Wyckoff and Raghotham Murthy",
  title =        "{Hive}: a warehousing solution over a map-reduce
                 framework",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1626--1629",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Satish:2009:TEB,
  author =       "Arjun Satish and Ramesh Jain and Amarnath Gupta",
  title =        "{Tolkien}: an event based storytelling system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1630--1633",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sarigol:2009:ESN,
  author =       "Emre Sarig{\"o}l and Oriana Riva and Patrick Stuedi
                 and Gustavo Alonso",
  title =        "Enabling social networking in ad hoc networks of
                 mobile phones",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1634--1637",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bao:2009:PVD,
  author =       "Zhuowei Bao and Sarah Cohen-Boulakia and Susan B.
                 Davidson and Pierrick Girard",
  title =        "{PDiffView}: viewing the difference in provenance of
                 workflow results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1638--1641",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deutch:2009:GOW,
  author =       "Daniel Deutch and Tova Milo and Tom Yam",
  title =        "Goal-oriented {Web}-site navigation for on-line
                 shoppers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1642--1645",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pereira:2009:AWQ,
  author =       "Fernando Pereira and Anand Rajaraman and Sunita
                 Sarawagi and William Tunstall-Pedoe and Gerhard Weikum
                 and Alon Halevy",
  title =        "Answering {Web} questions using structured data: dream
                 or reality?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1646--1646",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bernstein:2009:HBB,
  author =       "Philip A. Bernstein and Daniel J. Abadi and Michael J.
                 Cafarella and Joseph M. Hellerstein and Donald Kossmann
                 and Samuel Madden",
  title =        "How best to build {Web}-scale data managers?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1647--1647",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Manegold:2009:DAE,
  author =       "Stefan Manegold and Martin L. Kersten and Peter
                 Boncz",
  title =        "Database architecture evolution: mammals flourished
                 long before dinosaurs became extinct",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1648--1653",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dong:2009:DFR,
  author =       "Xin Luna Dong and Felix Naumann",
  title =        "Data fusion: resolving data conflicts for
                 integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1654--1655",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Heer:2009:DVS,
  author =       "Jeffrey Heer and Joseph M. Hellerstein",
  title =        "Data visualization and social data analysis",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1656--1657",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaudhuri:2009:KQR,
  author =       "Surajit Chaudhuri and Gautam Das",
  title =        "Keyword querying and ranking in databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1658--1659",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hadjieleftheriou:2009:EAS,
  author =       "Marios Hadjieleftheriou and Chen Li",
  title =        "Efficient approximate search on string collections",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1660--1661",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Srivastava:2009:ITD,
  author =       "Divesh Srivastava and Suresh Venkatasubramanian",
  title =        "Information theory for data management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1662--1663",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abadi:2009:COD,
  author =       "Daniel J. Abadi and Peter A. Boncz and Stavros
                 Harizopoulos",
  title =        "Column-oriented database systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "2",
  number =       "2",
  pages =        "1664--1665",
  month =        aug,
  year =         "2009",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:54:57 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Srivastava:2010:ERT,
  author =       "Divesh Srivastava and Lukasz Golab and Rick Greer and
                 Theodore Johnson and Joseph Seidel and Vladislav
                 Shkapenyuk and Oliver Spatscheck and Jennifer Yates",
  title =        "Enabling real time data analysis",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1--2",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Matsudaira:2010:HEB,
  author =       "Paul Matsudaira",
  title =        "High-end biological imaging generates very large
                 {$3$D+} and dynamic datasets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "3--3",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cho:2010:DWD,
  author =       "Junghoo Cho and Hector Garcia-Molina",
  title =        "Dealing with {Web} data: history and look ahead",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "4--4",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
  remark =       "10-year best paper award",
}

@Article{Kemme:2010:DRT,
  author =       "Bettina Kemme and Gustavo Alonso",
  title =        "Database replication: a tale of research across
                 communities",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "5--12",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
  remark =       "10-year best paper award",
}

@Article{Canim:2010:BDR,
  author =       "Mustafa Canim and Murat Kantarcio{\u{g}}lu and Bijit
                 Hore and Sharad Mehrotra",
  title =        "Building disclosure risk aware query optimizers for
                 relational databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "13--24",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Allard:2010:SPD,
  author =       "Tristan Allard and Nicolas Anciaux and Luc Bouganim
                 and Yanli Guo and Lionel Le Folgoc and Benjamin Nguyen
                 and Philippe Pucheral and Indrajit Ray and Indrakshi
                 Ray and Shaoyi Yin",
  title =        "Secure personal data servers: a vision paper",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "25--35",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fabbri:2010:PMR,
  author =       "Daniel Fabbri and Kristen LeFevre and Qiang Zhu",
  title =        "{PolicyReplay}: misconfiguration-response queries for
                 data breach reporting",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "36--47",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Curino:2010:SWD,
  author =       "Carlo Curino and Evan Jones and Yang Zhang and Sam
                 Madden",
  title =        "{Schism}: a workload-driven approach to database
                 replication and partitioning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "48--57",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Qin:2010:TTS,
  author =       "Lu Qin and Jeffrey Xu Yu and Lijun Chang",
  title =        "Ten thousand {SQLs}: parallel keyword queries
                 computing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "58--69",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Thomson:2010:CDD,
  author =       "Alexander Thomson and Daniel J. Abadi",
  title =        "The case for determinism in database systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "70--80",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alexe:2010:MCI,
  author =       "Bogdan Alexe and Mauricio Hern{\'a}ndez and Lucian
                 Popa and Wang-Chiew Tan",
  title =        "{MapMerge}: correlating independent schema mappings",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "81--92",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Greco:2010:CTC,
  author =       "Sergio Greco and Francesca Spezzano",
  title =        "Chase termination: a constraints rewriting approach",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "93--104",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Marnette:2010:SDE,
  author =       "Bruno Marnette and Giansalvatore Mecca and Paolo
                 Papotti",
  title =        "Scalable data exchange with functional dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "105--116",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kanza:2010:IRS,
  author =       "Yaron Kanza and Roy Levin and Eliyahu Safra and
                 Yehoshua Sagiv",
  title =        "Interactive route search in the presence of order
                 constraints",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "117--128",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lang:2010:EMM,
  author =       "Willis Lang and Jignesh M. Patel",
  title =        "Energy management for {MapReduce} clusters",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "129--139",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Baid:2010:TSK,
  author =       "Akanksha Baid and Ian Rae and Jiexing Li and AnHai
                 Doan and Jeffrey Naughton",
  title =        "Toward scalable keyword search over relational data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "140--149",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mozafari:2010:REN,
  author =       "Barzan Mozafari and Kai Zeng and Carlo Zaniolo",
  title =        "From regular expressions to nested words: unifying
                 languages and query execution for relational and {XML}
                 sequences",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "150--161",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Grust:2010:ASL,
  author =       "Torsten Grust and Jan Rittinger and Tom Schreiber",
  title =        "Avalanche-safe {LINQ} compilation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "162--172",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2010:TCF,
  author =       "Wenfei Fan and Jianzhong Li and Shuai Ma and Nan Tang
                 and Wenyuan Yu",
  title =        "Towards certain fixes with editing rules and master
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "173--184",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Herschel:2010:EMA,
  author =       "Melanie Herschel and Mauricio A. Hern{\'a}ndez",
  title =        "Explaining missing answers to {SPJUA} queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "185--196",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Beskales:2010:SRF,
  author =       "George Beskales and Ihab F. Ilyas and Lukasz Golab",
  title =        "Sampling the repairs of functional dependency
                 violations under hard constraints",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "197--207",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Menestrina:2010:EER,
  author =       "David Menestrina and Steven Euijong Whang and Hector
                 Garcia-Molina",
  title =        "Evaluating entity resolution results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "208--219",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chandramouli:2010:HPD,
  author =       "Badrish Chandramouli and Jonathan Goldstein and David
                 Maier",
  title =        "High-performance dynamic pattern matching over
                 disordered streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "220--231",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Botan:2010:SMA,
  author =       "Irina Botan and Roozbeh Derakhshan and Nihal Dindar
                 and Laura Haas and Ren{\'e}e J. Miller and Nesime
                 Tatbul",
  title =        "{SECRET}: a model for analysis of the execution
                 semantics of stream processing systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "232--243",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2010:RPS,
  author =       "Haopeng Zhang and Yanlei Diao and Neil Immerman",
  title =        "Recognizing patterns in streams with imprecise
                 timestamps",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "244--255",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Neumann:2010:XRF,
  author =       "Thomas Neumann and Gerhard Weikum",
  title =        "{x-RDF-3X}: fast querying, high update rates, and
                 consistency for {RDF} databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "256--263",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2010:GPM,
  author =       "Wenfei Fan and Jianzhong Li and Shuai Ma and Nan Tang
                 and Yinghui Wu and Yunpeng Wu",
  title =        "Graph pattern matching: from intractable to polynomial
                 time",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "264--275",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yildirim:2010:GSR,
  author =       "Hilmi Yildirim and Vineet Chaoji and Mohammed J.
                 Zaki",
  title =        "{GRAIL}: scalable reachability index for large
                 graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "276--284",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bu:2010:HEI,
  author =       "Yingyi Bu and Bill Howe and Magdalena Balazinska and
                 Michael D. Ernst",
  title =        "{HaLoop}: efficient iterative data processing on large
                 clusters",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "285--296",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Benedikt:2010:IVV,
  author =       "Michael Benedikt and Georg Gottlob",
  title =        "The impact of virtual views on containment",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "297--308",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Terwilliger:2010:UET,
  author =       "James F. Terwilliger and Lois M. L. Delcambre and
                 David Maier and Jeremy Steinhauer and Scott Britell",
  title =        "Updatable and evolvable transforms for virtual
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "309--319",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deutch:2010:NCM,
  author =       "Daniel Deutch and Ohad Greenshpan and Tova Milo",
  title =        "Navigating in complex mashed-up applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "320--329",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Melnik:2010:DIA,
  author =       "Sergey Melnik and Andrey Gubarev and Jing Jing Long
                 and Geoffrey Romer and Shiva Shivakumar and Matt Tolton
                 and Theo Vassilakis",
  title =        "{Dremel}: interactive analysis of {Web}-scale
                 datasets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "330--339",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhao:2010:GQO,
  author =       "Peixiang Zhao and Jiawei Han",
  title =        "On graph query optimization in large networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "340--351",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Martinenghi:2010:PRJ,
  author =       "Davide Martinenghi and Marco Tagliasacchi",
  title =        "Proximity rank join",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "352--363",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Vlachou:2010:IMI,
  author =       "Akrivi Vlachou and Christos Doulkeridis and Kjetil
                 N{\o}rv{\aa}g and Yannis Kotidis",
  title =        "Identifying the most influential data objects with
                 reverse top-$k$ queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "364--372",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2010:RTP,
  author =       "Xin Cao and Gao Cong and Christian S. Jensen",
  title =        "Retrieving top-$k$ prestige-based relevant spatial
                 {Web} objects",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "373--384",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2010:PLF,
  author =       "Lei Li and B. Aditya Prakash and Christos Faloutsos",
  title =        "Parsimonious linear fingerprinting for time series",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "385--396",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2010:HTM,
  author =       "Rui Zhang and Martin Stradling",
  title =        "The {HV-tree}: a memory hierarchy aware version
                 index",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "397--408",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pramanik:2010:TRQ,
  author =       "Sakti Pramanik and Alok Watve and Chad R. Meiners and
                 Alex Liu",
  title =        "Transforming range queries to equivalent box queries
                 to optimize page access",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "409--416",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guo:2010:RLU,
  author =       "Songtao Guo and Xin Luna Dong and Divesh Srivastava
                 and Remi Zajac",
  title =        "Record linkage with uniqueness constraints and
                 erroneous values",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "417--428",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ioannou:2010:FEA,
  author =       "Ekaterini Ioannou and Wolfgang Nejdl and Claudia
                 Nieder{\'e}e and Yannis Velegrakis",
  title =        "On-the-fly entity-aware query processing in the
                 presence of linkage",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "429--438",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yakout:2010:BBR,
  author =       "Mohamed Yakout and Ahmed K. Elmagarmid and Hazem
                 Elmeleegy and Mourad Ouzzani and Alan Qi",
  title =        "Behavior based record linkage",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "439--448",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Han:2010:IFC,
  author =       "Wook-Shin Han and Jinsoo Lee and Minh-Duc Pham and
                 Jeffrey Xu Yu",
  title =        "{iGraph}: a framework for comparisons of disk-based
                 graph indexing techniques",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "449--459",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Schad:2010:RMC,
  author =       "J{\"o}rg Schad and Jens Dittrich and Jorge-Arnulfo
                 Quian{\'e}-Ruiz",
  title =        "Runtime measurements in the cloud: observing,
                 analyzing, and reducing variance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "460--471",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jiang:2010:PMD,
  author =       "Dawei Jiang and Beng Chin Ooi and Lei Shi and Sai Wu",
  title =        "The performance of {MapReduce}: an in-depth study",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "472--483",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kopcke:2010:EER,
  author =       "Hanna K{\"o}pcke and Andreas Thor and Erhard Rahm",
  title =        "Evaluation of entity resolution approaches on
                 real-world match problems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "484--493",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nykiel:2010:MSA,
  author =       "Tomasz Nykiel and Michalis Potamias and Chaitanya
                 Mishra and George Kollios and Nick Koudas",
  title =        "{MRShare}: sharing across multiple queries in
                 {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "494--505",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Vo:2010:TET,
  author =       "Hoang Tam Vo and Chun Chen and Beng Chin Ooi",
  title =        "Towards elastic transactional cloud storage with range
                 query support",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "506--514",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dittrich:2010:HMY,
  author =       "Jens Dittrich and Jorge-Arnulfo Quian{\'e}-Ruiz and
                 Alekh Jindal and Yagiz Kargin and Vinay Setty and
                 J{\"o}rg Schad",
  title =        "{Hadoop++}: making a yellow elephant run like a
                 cheetah (without it even noticing)",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "515--529",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bruno:2010:SLR,
  author =       "Nicolas Bruno and Vivek Narasayya and Ravi
                 Ramamurthy",
  title =        "Slicing long-running queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "530--541",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tzoumas:2010:SAH,
  author =       "Kostas Tzoumas and Amol Deshpande and Christian S.
                 Jensen",
  title =        "Sharing-aware horizontal partitioning for exploiting
                 correlations during query processing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "542--553",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cali:2010:APO,
  author =       "Andrea Cal{\`\i} and Georg Gottlob and Andreas
                 Pieris",
  title =        "Advanced processing for ontological queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "554--565",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Parameswaran:2010:TWC,
  author =       "Aditya Parameswaran and Hector Garcia-Molina and Anand
                 Rajaraman",
  title =        "Towards the {Web} of concepts: extracting concepts
                 from large datasets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "566--577",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gulhane:2010:ECR,
  author =       "Pankaj Gulhane and Rajeev Rastogi and Srinivasan H.
                 Sengamedu and Ashwin Tengli",
  title =        "Exploiting content redundancy for {Web} information
                 extraction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "578--587",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2010:ARR,
  author =       "Bin Liu and Laura Chiticariu and Vivian Chu and H. V.
                 Jagadish and Frederick R. Reiss",
  title =        "Automatic rule refinement for information extraction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "588--597",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pang:2010:ETS,
  author =       "HweeHwa Pang and Xuhua Ding and Xiaokui Xiao",
  title =        "Embellishing text search queries to protect user
                 privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "598--607",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chaytor:2010:SDR,
  author =       "Rhonda Chaytor and Ke Wang",
  title =        "Small domain randomization: same privacy, more
                 utility",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "608--618",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Papadopoulos:2010:NNS,
  author =       "Stavros Papadopoulos and Spiridon Bakiras and Dimitris
                 Papadias",
  title =        "Nearest neighbor search with strong location privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "619--629",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kimura:2010:UPI,
  author =       "Hideaki Kimura and Samuel Madden and Stanley B.
                 Zdonik",
  title =        "{UPI}: a primary index for uncertain databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "630--637",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2010:RCP,
  author =       "Jian Li and Amol Deshpande",
  title =        "Ranking continuous probabilistic datasets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "638--649",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lian:2010:SSJ,
  author =       "Xiang Lian and Lei Chen",
  title =        "Set similarity join on probabilistic data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "650--659",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Woods:2010:CED,
  author =       "Louis Woods and Jens Teubner and Gustavo Alonso",
  title =        "Complex event detection at wire speed with {FPGAs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "660--669",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fang:2010:DCG,
  author =       "Wenbin Fang and Bingsheng He and Qiong Luo",
  title =        "Database compression on graphics processors",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "670--680",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Johnson:2010:ASA,
  author =       "Ryan Johnson and Ippokratis Pandis and Radu Stoica and
                 Manos Athanassoulis and Anastasia Ailamaki",
  title =        "{Aether}: a scalable approach to logging",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "681--692",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Macropol:2010:SDB,
  author =       "Kathy Macropol and Ambuj Singh",
  title =        "Scalable discovery of best clusters on large graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "693--702",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Smola:2010:APT,
  author =       "Alexander Smola and Shravan Narayanamurthy",
  title =        "An architecture for parallel topic models",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "703--710",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ganti:2010:KFI,
  author =       "Venkatesh Ganti and Yeye He and Dong Xin",
  title =        "{Keyword++}: a framework to improve keyword search
                 over entity databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "711--722",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2010:SMR,
  author =       "Zhenhui Li and Bolin Ding and Jiawei Han and Roland
                 Kays",
  title =        "{Swarm}: mining relaxed temporal moving object
                 clusters",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "723--734",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2010:AUP,
  author =       "Su Chen and Beng Chin Ooi and Zhenjie Zhang",
  title =        "An adaptive updating protocol for reducing moving
                 object database workload",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "735--746",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kellaris:2010:SPC,
  author =       "Georgios Kellaris and Kyriakos Mouratidis",
  title =        "Shortest path computation on air indexes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "747--757",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xu:2010:EES,
  author =       "Jia Xu and Zhenjie Zhang and Anthony K. H. Tung and Ge
                 Yu",
  title =        "Efficient and effective similarity search over
                 probabilistic data based on {Earth Mover's Distance}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "758--769",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Benedikt:2010:PXM,
  author =       "Michael Benedikt and Evgeny Kharlamov and Dan Olteanu
                 and Pierre Senellart",
  title =        "Probabilistic {XML} via {Markov Chains}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "770--781",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Arumugam:2010:MRR,
  author =       "Subi Arumugam and Fei Xu and Ravi Jampani and
                 Christopher Jermaine and Luis L. Perez and Peter J.
                 Haas",
  title =        "{MCDB-R}: risk analysis in the database",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "782--793",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wick:2010:SPD,
  author =       "Michael Wick and Andrew McCallum and Gerome Miklau",
  title =        "Scalable probabilistic databases with factor graphs
                 and {MCMC}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "794--804",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2010:MCF,
  author =       "Meihui Zhang and Marios Hadjieleftheriou and Beng Chin
                 Ooi and Cecilia M. Procopiuc and Divesh Srivastava",
  title =        "On multi-column foreign key discovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "805--814",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheng:2010:EEE,
  author =       "Reynold Cheng and Eric Lo and Xuan S. Yang and
                 Ming-Hay Luk and Xiang Li and Xike Xie",
  title =        "Explore or exploit?: effective strategies for
                 disambiguating large databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "815--825",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Soliman:2010:BRM,
  author =       "Mohamed A. Soliman and Ihab F. Ilyas and Mina Saleeb",
  title =        "Building ranked mashups of unstructured sources with
                 uncertain information",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "826--837",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Raissi:2010:CCS,
  author =       "Chedy Ra{\"\i}ssi and Jian Pei and Thomas Kister",
  title =        "Computing closed skycubes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "838--847",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lo:2010:GDQ,
  author =       "Eric Lo and Nick Cheng and Wing-Kai Hon",
  title =        "Generating databases for query workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "848--859",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2010:PTJ,
  author =       "Minji Wu and Laure Berti-{\'E}quille and Am{\'e}lie
                 Marian and Cecilia M. Procopiuc and Divesh Srivastava",
  title =        "Processing top-$k$ join queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "860--870",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Martinez-Palau:2010:TWR,
  author =       "Xavier Martinez-Palau and David Dominguez-Sal and
                 Josep Lluis Larriba-Pey",
  title =        "Two-way replacement selection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "871--881",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Maneth:2010:XWQ,
  author =       "Sebastian Maneth and Kim Nguyen",
  title =        "{XPath} whole query optimization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "882--893",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Grimsmo:2010:FOT,
  author =       "Nils Grimsmo and Truls A. Bj{\o}rklund and Magnus Lie
                 Hetland",
  title =        "Fast optimal twig joins",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "894--905",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Benedikt:2010:DIX,
  author =       "Michael Benedikt and James Cheney",
  title =        "Destabilizers and independence of {XML} updates",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "906--917",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2010:SWH,
  author =       "Ziyang Liu and Qihong Shao and Yi Chen",
  title =        "Searching workflows with hierarchical views",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "918--927",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pandis:2010:DOT,
  author =       "Ippokratis Pandis and Ryan Johnson and Nikos
                 Hardavellas and Anastasia Ailamaki",
  title =        "Data-oriented transaction execution",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "928--939",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deutch:2010:OTQ,
  author =       "Daniel Deutch and Tova Milo and Neoklis Polyzotis and
                 Tom Yam",
  title =        "Optimal top-$k$ query evaluation for weighted business
                 processes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "940--951",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2010:BSM,
  author =       "Guozhang Wang and Marcos Vaz Salles and Benjamin
                 Sowell and Xun Wang and Tuan Cao and Alan Demers and
                 Johannes Gehrke and Walker White",
  title =        "Behavioral simulations in {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "952--963",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ge:2010:TSS,
  author =       "Tingjian Ge and Stan Zdonik",
  title =        "{A*-tree}: a structure for storage and modeling of
                 uncertain multidimensional arrays",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "964--974",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Aggarwal:2010:DPM,
  author =       "Charu C. Aggarwal and Yao Li and Philip S. Yu and
                 Ruoming Jin",
  title =        "On dense pattern mining in graph streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "975--984",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yiu:2010:EPD,
  author =       "Man Lung Yiu and Leong Hou U. and Simonas Saltenis and
                 Kostas Tzoumas",
  title =        "Efficient proximity detection among mobile users via
                 self-tuning policies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "985--996",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Potamias:2010:KNN,
  author =       "Michalis Potamias and Francesco Bonchi and Aristides
                 Gionis and George Kollios",
  title =        "k-nearest neighbors in uncertain graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "997--1008",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2010:MSS,
  author =       "Xin Cao and Gao Cong and Christian S. Jensen",
  title =        "Mining significant semantic locations from {GPS}
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1009--1020",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hay:2010:BAD,
  author =       "Michael Hay and Vibhor Rastogi and Gerome Miklau and
                 Dan Suciu",
  title =        "Boosting the accuracy of differentially private
                 histograms through consistency",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1021--1032",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2010:UIP,
  author =       "Jianneng Cao and Panagiotis Karras and Chedy
                 Ra{\"\i}ssi and Kian-Lee Tan",
  title =        "$\rho$-uncertainty: inference-proof transaction
                 anonymization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1033--1044",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cormode:2010:MMM,
  author =       "Graham Cormode and Divesh Srivastava and Ninghui Li
                 and Tiancheng Li",
  title =        "Minimizing minimality and maximizing utility:
                 analyzing method-based attacks on anonymized data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1045--1056",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2010:QPI,
  author =       "Daisy Zhe Wang and Michael J. Franklin and Minos
                 Garofalakis and Joseph M. Hellerstein",
  title =        "Querying probabilistic information extraction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1057--1067",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sen:2010:ROF,
  author =       "Prithviraj Sen and Amol Deshpande and Lise Getoor",
  title =        "Read-once functions and query evaluation in
                 probabilistic databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1068--1079",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agrawal:2010:FUD,
  author =       "Parag Agrawal and Anish Das Sarma and Jeffrey Ullman
                 and Jennifer Widom",
  title =        "Foundations of uncertain-data integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1080--1090",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mathioudakis:2010:IAD,
  author =       "Michael Mathioudakis and Nilesh Bansal and Nick
                 Koudas",
  title =        "Identifying, attributing and describing spatial
                 bursts",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1091--1102",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kimura:2010:CCA,
  author =       "Hideaki Kimura and George Huo and Alexander Rasin and
                 Samuel Madden and Stanley B. Zdonik",
  title =        "{CORADD}: correlation aware database designer for
                 materialized views and indexes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1103--1113",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nanongkai:2010:RMR,
  author =       "Danupon Nanongkai and Atish Das Sarma and Ashwin Lall
                 and Richard J. Lipton and Jun Xu",
  title =        "Regret-minimizing representative databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1114--1124",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Arai:2010:ACA,
  author =       "Benjamin Arai and Gautam Das and Dimitrios Gunopulos
                 and Vagelis Hristidis and Nick Koudas",
  title =        "An access cost-aware approach for object retrieval
                 over multiple sources",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1125--1136",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abhirama:2010:SPC,
  author =       "M. Abhirama and Sourjya Bhaumik and Atreyee Dey and
                 Harsh Shrimal and Jayant R. Haritsa",
  title =        "On the stability of plan costs and the costs of plan
                 stability",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1137--1148",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Herodotou:2010:XST,
  author =       "Herodotos Herodotou and Shivnath Babu",
  title =        "{Xplus}: a {SQL}-tuning-aware query optimizer",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1149--1160",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2010:GHR,
  author =       "Wenfei Fan and Jianzhong Li and Shuai Ma and Hongzhi
                 Wang and Yinghui Wu",
  title =        "Graph homomorphism revisited for graph matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1161--1172",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kandhan:2010:SFS,
  author =       "Ramakrishnan Kandhan and Nikhil Teletia and Jignesh M.
                 Patel",
  title =        "{SigMatch}: fast and scalable multi-pattern matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1173--1184",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2010:SSI,
  author =       "Shijie Zhang and Jiong Yang and Wei Jin",
  title =        "{SAPPER}: subgraph indexing and approximate matching
                 in large graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1185--1194",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2010:TIS,
  author =       "Yinan Li and Bingsheng He and Robin Jun Yang and Qiong
                 Luo and Ke Yi",
  title =        "Tree indexing on solid state drives",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1195--1206",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2010:EBT,
  author =       "Sai Wu and Dawei Jiang and Beng Chin Ooi and Kun-Lung
                 Wu",
  title =        "Efficient {B-tree} based indexing for cloud data
                 processing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1207--1218",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2010:TJE,
  author =       "Jiannan Wang and Jianhua Feng and Guoliang Li",
  title =        "{Trie-join}: efficient trie-based string similarity
                 joins with edit-distance constraints",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1219--1230",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sharifzadeh:2010:VTR,
  author =       "Mehdi Sharifzadeh and Cyrus Shahabi",
  title =        "{VoR-tree}: {R-trees} with {Voronoi} diagrams for
                 efficient processing of spatial nearest neighbor
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1231--1242",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Deepak:2010:ERR,
  author =       "P. Deepak and Prasad M. Deshpande",
  title =        "Efficient {RkNN} retrieval with arbitrary non-metric
                 similarity measures",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1243--1254",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2010:ESE,
  author =       "Shiming Zhang and Nikos Mamoulis and David W. Cheung
                 and Ben Kao",
  title =        "Efficient skyline evaluation over partially ordered
                 domains",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1255--1266",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wei:2010:AHO,
  author =       "Mingzhu Wei and Elke A. Rundensteiner and Murali
                 Mani",
  title =        "Achieving high output quality under limited resources
                 through structure-based spilling in {XML} streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1267--1278",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mihaylov:2010:DJO,
  author =       "Svilen R. Mihaylov and Marie Jacob and Zachary G. Ives
                 and Sudipto Guha",
  title =        "Dynamic join optimization in multi-hop wireless sensor
                 networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1279--1290",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Akdere:2010:DSC,
  author =       "Mert Akdere and U{\u{g}}ur {\c{C}}etintemel and Eli
                 Upfal",
  title =        "Database-support for continuous prediction queries
                 over streaming data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1291--1301",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tran:2010:CAU,
  author =       "Thanh T. L. Tran and Andrew McGregor and Yanlei Diao
                 and Liping Peng and Anna Liu",
  title =        "Conditioning and aggregating uncertain data streams:
                 going beyond expectations",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1302--1313",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Glavic:2010:TUB,
  author =       "Boris Glavic and Gustavo Alonso and Ren{\'e}e J.
                 Miller and Laura M. Haas",
  title =        "{TRAMP}: understanding the behavior of schema mappings
                 through provenance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1314--1325",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Whang:2010:ERE,
  author =       "Steven Euijong Whang and Hector Garcia-Molina",
  title =        "Entity resolution with evolving rules",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1326--1337",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Limaye:2010:ASW,
  author =       "Girija Limaye and Sunita Sarawagi and Soumen
                 Chakrabarti",
  title =        "Annotating and searching {Web} tables using entities,
                 types and relationships",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1338--1347",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bedathur:2010:IPM,
  author =       "Srikanta Bedathur and Klaus Berberich and Jens
                 Dittrich and Nikos Mamoulis and Gerhard Weikum",
  title =        "Interesting-phrase mining for ad-hoc text analytics",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1348--1357",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dong:2010:GDC,
  author =       "Xin Luna Dong and Laure Berti-Equille and Yifan Hu and
                 Divesh Srivastava",
  title =        "Global detection of complex copying relationships
                 between sources",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1358--1369",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{DeCapitanidiVimercati:2010:FLA,
  author =       "Sabrina {De Capitani di Vimercati} and Sara Foresti
                 and Sushil Jajodia and Stefano Paraboschi and
                 Pierangela Samarati",
  title =        "Fragments and loose associations: respecting privacy
                 in data publishing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1370--1381",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fusco:2010:NFF,
  author =       "Francesco Fusco and Marc Ph. Stoecklin and Michail
                 Vlachos",
  title =        "{NET-FLi}: on-the-fly compression, archiving and
                 indexing of streaming network traffic",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1382--1393",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zou:2010:SRQ,
  author =       "Qiong Zou and Huayong Wang and Robert Soul{\'e} and
                 Martin Hirzel and Henrique Andrade and Bu{\u{g}}ra
                 Gedik and Kun-Lung Wu",
  title =        "From a stream of relational queries to distributed
                 stream processing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1394--1405",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mah:2010:UUA,
  author =       "James T. L. Mah and Danny C. C. Poo and Shaojiang
                 Cai",
  title =        "{UASMAs} (universal automated {SNP} mapping
                 algorithms): a set of algorithms to instantaneously map
                 {SNPs} in real time to aid functional {SNP} discovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1406--1413",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Debnath:2010:FHT,
  author =       "Biplob Debnath and Sudipta Sengupta and Jin Li",
  title =        "{FlashStore}: high throughput persistent key-value
                 store",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1414--1425",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xin:2010:MDA,
  author =       "Reynold S. Xin and William McLaren and Patrick
                 Dantressangle and Steve Schormann and Sam Lightstone
                 and Maria Schwenger",
  title =        "{MEET DB2}: automated database migration evaluation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1426--1434",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Canim:2010:SBE,
  author =       "Mustafa Canim and George A. Mihaila and Bishwaranjan
                 Bhattacharjee and Kenneth A. Ross and Christian A.
                 Lang",
  title =        "{SSD} bufferpool extensions for database systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1435--1446",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Loboz:2010:DWM,
  author =       "Charles Loboz and Slawek Smyl and Suman Nath",
  title =        "{DataGarage}: warehousing massive performance data on
                 commodity servers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1447--1458",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2010:CHP,
  author =       "Songting Chen",
  title =        "{Cheetah}: a high performance, custom data warehouse
                 on top of {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1459--1468",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Orair:2010:DBO,
  author =       "Gustavo H. Orair and Carlos H. C. Teixeira Wagner
                 {Meira, Jr.} and Ye Wang and Srinivasan Parthasarathy",
  title =        "Distance-based outlier detection: consolidation and
                 renewed bearing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1469--1480",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kim:2010:ALM,
  author =       "Young-Seok Kim and Heegyu Jin and Kyoung-Gu Woo",
  title =        "Adaptive logging for mobile device",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1481--1492",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pesti:2010:RSL,
  author =       "Peter Pesti and Ling Liu and Bhuvan Bamba and Arun
                 Iyengar and Matt Weber",
  title =        "{RoadTrack}: scaling location updates for mobile
                 clients on road networks with query awareness",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1493--1504",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Si:2010:CID,
  author =       "Xiance Si and Edward Y. Chang and Zolt{\'a}n
                 Gy{\"o}ngyi and Maosong Sun",
  title =        "Confucius and its intelligent disciples: integrating
                 social with search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1505--1516",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Haritsa:2010:PDQ,
  author =       "Jayant R. Haritsa",
  title =        "The {Picasso} database query optimizer visualizer",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1517--1520",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2010:CED,
  author =       "Ziyang Liu and Sivaramakrishnan Natarajan and Bin He
                 and Hui-I Hsiao and Yi Chen",
  title =        "{CODS}: evolving data efficiently and scalably in
                 column oriented databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1521--1524",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sadoghi:2010:EEP,
  author =       "Mohammad Sadoghi and Martin Labrecque and Harsh Singh
                 and Warren Shum and Hans-Arno Jacobsen",
  title =        "Efficient event processing through reconfigurable
                 hardware for algorithmic trading",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1525--1528",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Levandoski:2010:CCP,
  author =       "Justin J. Levandoski and Mohamed F. Mokbel and Mohamed
                 E. Khalefa",
  title =        "{CareDB}: a context and preference-aware
                 location-based database system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1529--1532",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kossmann:2010:CMC,
  author =       "Donald Kossmann and Tim Kraska and Simon Loesing and
                 Stephan Merkli and Raman Mittal and Flavio
                 Pfaffhauser",
  title =        "{Cloudy}: a modular cloud storage system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1533--1536",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kazemitabar:2010:GSQ,
  author =       "Seyed Jalal Kazemitabar and Ugur Demiryurek and
                 Mohamed Ali and Afsin Akdogan and Cyrus Shahabi",
  title =        "Geospatial stream query processing using {Microsoft
                 SQL Server StreamInsight}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1537--1540",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dyreson:2010:UXT,
  author =       "Curtis E. Dyreson and Sourav S. Bhowmick and
                 Kirankanth Mallampalli",
  title =        "Using {XMorph} to transform {XML} data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1541--1544",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2010:ACE,
  author =       "Di Wang and Elke A. Rundensteiner and Han Wang and
                 Richard T. {Ellison III}",
  title =        "Active complex event processing: applications in
                 real-time health care",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1545--1548",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Schreiber:2010:TNP,
  author =       "Tom Schreiber and Simone Bonetti and Torsten Grust and
                 Manuel Mayr and Jan Rittinger",
  title =        "Thirteen new players in the team: a {FERRY}-based
                 {LINQ} to {SQL} provider",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1549--1552",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abiteboul:2010:AEC,
  author =       "Serge Abiteboul and Pierre Bourhis and Bogdan Marinoiu
                 and Alban Galland",
  title =        "{AXART}: enabling collaborative work with {AXML}
                 artifacts",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1553--1556",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{McConnell:2010:IAF,
  author =       "Christopher McConnell and Fan Ping and Jeong-Hyon
                 Hwang",
  title =        "{iFlow}: an approach for fast and reliable
                 {Internet-scale} stream processing utilizing detouring
                 and replication",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1557--1560",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kantere:2010:PCT,
  author =       "Verena Kantere and Maher Manoubi and Iluju Kiringa and
                 Timos Sellis and John Mylopoulos",
  title =        "Peer coordination through distributed triggers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1561--1564",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2010:SSY,
  author =       "Hao Wu and Guoliang Li and Chen Li and Lizhu Zhou",
  title =        "{Seaform}: search-as-you-type in forms",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1565--1568",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Strotgen:2010:TSE,
  author =       "Jannik Str{\"o}tgen and Michael Gertz",
  title =        "{TimeTrails}: a system for exploring spatio-temporal
                 information in documents",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1569--1572",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pound:2010:QEF,
  author =       "Jeffrey Pound and Ihab F. Ilyas and Grant Weddell",
  title =        "{QUICK}: expressive and flexible search over knowledge
                 bases and text collections",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1573--1576",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kwietniewski:2010:TXD,
  author =       "Marcin Kwietniewski and Jarek Gryz and Stephanie
                 Hazlewood and Paul Van Run",
  title =        "Transforming {XML} documents as schemas evolve",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1577--1580",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2010:XCT,
  author =       "Ziyang Liu and Sivaramakrishnan Natarajan and Peng Sun
                 and Stephen Booher and Tim Meehan and Robert Winkler
                 and Yi Chen",
  title =        "{XSACT}: a comparison tool for structured search
                 results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1581--1584",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Abdessalem:2010:OLT,
  author =       "Talel Abdessalem and Bogdan Cautis and Nora
                 Derouiche",
  title =        "{ObjectRunner}: lightweight, targeted extraction and
                 querying of structured {Web} data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1585--1588",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Elbassuoni:2010:RRW,
  author =       "Shady Elbassuoni and Katja Hose and Steffen Metzger
                 and Ralf Schenkel",
  title =        "{ROXXI}: {Reviving} witness {dOcuments} to {eXplore
                 eXtracted Information}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1589--1592",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Termehchy:2010:EUD,
  author =       "Arash Termehchy and Marianne Winslett",
  title =        "{EXTRUCT}: using deep structural information in {XML}
                 keyword search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1593--1596",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Akbarnejad:2010:SQR,
  author =       "Javad Akbarnejad and Gloria Chatzopoulou and Magdalini
                 Eirinaki and Suju Koshy and Sarika Mittal and Duc On
                 and Neoklis Polyzotis and Jothi S. Vindhiya Varman",
  title =        "{SQL QueRIE} recommendations",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1597--1600",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ang:2010:PCM,
  author =       "Hock Hee Ang and Vivekanand Gopalkrishnan and Wee
                 Keong Ng and Steven C. H. Hoi",
  title =        "{P2PDocTagger}: content management through automated
                 {P2P} collaborative tagging",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1601--1604",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Setty:2010:IEI,
  author =       "Vinay Setty and Srikanta Bedathur and Klaus Berberich
                 and Gerhard Weikum",
  title =        "{InZeit}: efficiently identifying insightful time
                 points",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1605--1608",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sun:2010:IIT,
  author =       "Aixin Sun and Sourav S. Bhowmick and Yao Liu",
  title =        "{iAVATAR}: an interactive tool for finding and
                 visualizing visual-representative tags in image
                 search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1609--1612",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kabisch:2010:DWI,
  author =       "Thomas Kabisch and Eduard C. Dragut and Clement Yu and
                 Ulf Leser",
  title =        "Deep {Web} integration with {VisQI}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1613--1616",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dong:2010:SST,
  author =       "Xin Luna Dong and Laure Berti-Equille and Yifan Hu and
                 Divesh Srivastava",
  title =        "{SOLOMON}: seeking the truth via copying detection",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1617--1620",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hentschel:2010:JTD,
  author =       "Martin Hentschel and Laura Haas and Ren{\'e}e J.
                 Miller",
  title =        "Just-in-time data integration in action",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1621--1624",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alexandrov:2010:MPD,
  author =       "Alexander Alexandrov and Max Heimel and Volker Markl
                 and Dominic Battr{\'e} and Fabian Hueske and Erik
                 Nijkamp and Stephan Ewen and Odej Kao and Daniel
                 Warneke",
  title =        "Massively parallel data analysis with {PACTs} on
                 {Nephele}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1625--1628",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Middelfart:2010:UST,
  author =       "Morten Middelfart and Torben Bach Pedersen",
  title =        "Using sentinel technology in the {TARGIT BI} suite",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1629--1632",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gunnemann:2010:CIC,
  author =       "Stephan G{\"u}nnemann and Ines F{\"a}rber and Hardy
                 Kremer and Thomas Seidl",
  title =        "{CoDA}: interactive cluster based concept discovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1633--1636",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bergamaschi:2010:KSK,
  author =       "Sonia Bergamaschi and Elton Domnori and Francesco
                 Guerra and Mirko Orsini and Raquel Trillo Lado and
                 Yannis Velegrakis",
  title =        "{Keymantic}: semantic keyword-based searching in data
                 integration systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1637--1640",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Golab:2010:DAE,
  author =       "Lukasz Golab and Howard Karloff and Flip Korn and
                 Divesh Srivastava",
  title =        "Data {Auditor}: exploring data quality and semantics
                 using pattern tableaux",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1641--1644",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nori:2010:DCP,
  author =       "Anil K. Nori",
  title =        "Distributed caching platforms",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1645--1646",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agrawal:2010:BDC,
  author =       "Divyakant Agrawal and Sudipto Das and Amr {El
                 Abbadi}",
  title =        "Big data and cloud computing: new wine or just new
                 bottles?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1647--1648",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Samet:2010:TSS,
  author =       "Hanan Samet",
  title =        "Techniques for similarity searching in multimedia
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1649--1650",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Etzion:2010:EPP,
  author =       "Opher Etzion",
  title =        "Event processing: past, present and future",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1651--1652",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Renz:2010:SSM,
  author =       "Matthias Renz and Reynold Cheng and Hans-Peter
                 Kriegel",
  title =        "Similarity search and mining in uncertain databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1653--1654",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Muthukrishnan:2010:DMM,
  author =       "S. Muthukrishnan",
  title =        "Data management and mining in {Internet AD} systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "3",
  number =       "1--2",
  pages =        "1655--1656",
  month =        sep,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:02 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kling:2010:GEE,
  author =       "Patrick Kling and M. Tamer {\"O}zsu and Khuzaima
                 Daudjee",
  title =        "Generating efficient execution plans for vertically
                 partitioned {XML} databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "1",
  pages =        "1--11",
  month =        oct,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lian:2010:GFH,
  author =       "Xiang Lian and Lei Chen",
  title =        "A generic framework for handling uncertain data with
                 local correlations",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "1",
  pages =        "12--21",
  month =        oct,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Khoussainova:2010:SCA,
  author =       "Nodira Khoussainova and YongChul Kwon and Magdalena
                 Balazinska and Dan Suciu",
  title =        "{SnipSuggest}: context-aware autocompletion for
                 {SQL}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "1",
  pages =        "22--33",
  month =        oct,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Meliou:2010:CCR,
  author =       "Alexandra Meliou and Wolfgang Gatterbauer and
                 Katherine F. Moore and Dan Suciu",
  title =        "The complexity of causality and responsibility for
                 query answers and non-answers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "1",
  pages =        "34--45",
  month =        oct,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sagy:2010:DTQ,
  author =       "Guy Sagy and Daniel Keren and Izchak Sharfman and
                 Assaf Schuster",
  title =        "Distributed threshold querying of general functions by
                 a difference of monotonic representation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "46--57",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2010:TBD,
  author =       "Nan Wang and Jingbo Zhang and Kian-Lee Tan and Anthony
                 K. H. Tung",
  title =        "On triangulation-based dense neighborhood graph
                 discovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "58--68",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rice:2010:GIR,
  author =       "Michael Rice and Vassilis J. Tsotras",
  title =        "Graph indexing of road networks for shortest path
                 queries with label restrictions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "69--80",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Qian:2010:CUF,
  author =       "Li Qian and Kristen LeFevre and H. V. Jagadish",
  title =        "{CRIUS}: user-friendly database design",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "81--92",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rocha-Junior:2010:EPT,
  author =       "Jo{\~a}o B. Rocha-Junior and Akrivi Vlachou and
                 Christos Doulkeridis and Kjetil N{\o}rv{\aa}g",
  title =        "Efficient processing of top-$k$ spatial preference
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "93--104",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Grund:2010:HMM,
  author =       "Martin Grund and Jens Kr{\"u}ger and Hasso Plattner
                 and Alexander Zeier and Philippe Cudre-Mauroux and
                 Samuel Madden",
  title =        "{HYRISE}: a main memory hybrid storage engine",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "105--116",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Curino:2010:URI,
  author =       "Carlo A. Curino and Hyun Jin Moon and Alin Deutsch and
                 Carlo Zaniolo",
  title =        "Update rewriting and integrity constraint maintenance
                 in a schema evolution support system: {PRISM++}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "117--128",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Oro:2010:SEX,
  author =       "Ermelinda Oro and Massimo Ruffolo and Steffen Staab",
  title =        "{SXPath}: extending {XPath} towards spatial querying
                 on {Web} documents",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "129--140",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yuan:2010:PPP,
  author =       "Mingxuan Yuan and Lei Chen and Philip S. Yu",
  title =        "Personalized privacy protection in social networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "2",
  pages =        "141--150",
  month =        nov,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:15 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Toda:2010:PAA,
  author =       "Guilherme A. Toda and Eli Cortez and Altigran S. da
                 Silva and Edleno de Moura",
  title =        "A probabilistic approach for automatically filling
                 form-based {Web} interfaces",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "3",
  pages =        "151--160",
  month =        dec,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:16 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Papadimitriou:2010:OUB,
  author =       "Panagiotis Papadimitriou and Hector Garcia-Molina and
                 Ali Dasdan and Santanu Kolay",
  title =        "Output {URL} bidding",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "3",
  pages =        "161--172",
  month =        dec,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:16 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bahmani:2010:FIP,
  author =       "Bahman Bahmani and Abdur Chowdhury and Ashish Goel",
  title =        "Fast incremental and personalized {PageRank}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "3",
  pages =        "173--184",
  month =        dec,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:16 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this paper, we analyze the efficiency of Monte
                 Carlo methods for incremental computation of PageRank,
                 personalized PageRank, and similar random walk based
                 methods (with focus on SALSA), on large-scale
                 dynamically evolving social networks. We assume that
                 the graph of friendships is stored in distributed
                 shared memory, as is the case for large social networks
                 such as Twitter.\par

                 For global PageRank, we assume that the social network
                 has $n$ nodes, and $m$ adversarially chosen edges
                 arrive in a random order. We show that with a reset
                 probability of $\epsilon$, the expected total work
                 needed to maintain an accurate estimate (using the
                 Monte Carlo method) of the PageRank of every node at
                 all times is $O(n \ln m / \epsilon^2)$. This is
                 significantly better than all known bounds for
                 incremental PageRank. For instance, if we naively
                 recompute the PageRanks as each edge arrives, the
                 simple power iteration method needs $\Omega(m^2 / \ln(1
                 / (1 - \epsilon)))$ total time and the Monte Carlo
                 method needs $O(m n / \epsilon)$ total time; both are
                 prohibitively expensive. We also show that we can
                 handle deletions equally efficiently.\par

                 We then study the computation of the top $k$
                 personalized PageRanks starting from a seed node,
                 assuming that personalized PageRanks follow a power-law
                 with exponent $< 1$. We show that if we store $R > q
                 \ln n$ random walks starting from every node for large
                 enough constant $q$ (using the approach outlined for
                 global PageRank), then the expected number of calls
                 made to the distributed social network database is
                 $O(k/(R^{(1 - \alpha) / \alpha}))$. We also present
                 experimental results from the social networking site,
                 Twitter, verifying our assumptions and analyses. The
                 overall result is that this algorithm is fast enough
                 for real-time queries over a dynamic social network.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2010:QES,
  author =       "Jongwuk Lee and Seung-won Hwang",
  title =        "{QSkycube}: efficient skycube computation using
                 point-based space partitioning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "3",
  pages =        "185--196",
  month =        dec,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:16 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2010:ZEI,
  author =       "Bin Liu and Chee-Yong Chan",
  title =        "{ZINC}: efficient indexing for skyline computation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "3",
  pages =        "197--207",
  month =        dec,
  year =         "2010",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:16 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rastogi:2011:LSC,
  author =       "Vibhor Rastogi and Nilesh Dalvi and Minos
                 Garofalakis",
  title =        "Large-scale collective entity matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "4",
  pages =        "208--218",
  month =        jan,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:17 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dalvi:2011:AWL,
  author =       "Nilesh Dalvi and Ravi Kumar and Mohamed Soliman",
  title =        "Automatic wrappers for large scale {Web} extraction",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "4",
  pages =        "219--230",
  month =        jan,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:17 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2011:FSM,
  author =       "Xintian Yang and Srinivasan Parthasarathy and P.
                 Sadayappan",
  title =        "Fast sparse matrix-vector multiplication on {GPUs}:
                 implications for graph mining",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "4",
  pages =        "231--242",
  month =        jan,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:17 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rao:2011:UPB,
  author =       "Jun Rao and Eugene J. Shekita and Sandeep Tata",
  title =        "Using {Paxos} to build a scalable, consistent, and
                 highly available datastore",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "4",
  pages =        "243--254",
  month =        jan,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:17 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ding:2011:FSI,
  author =       "Bolin Ding and Arnd Christian K{\"o}nig",
  title =        "Fast set intersection in memory",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "4",
  pages =        "255--266",
  month =        jan,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:17 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Parameswaran:2011:HAG,
  author =       "Aditya Parameswaran and Anish Das Sarma and Hector
                 Garcia-Molina and Neoklis Polyzotis and Jennifer
                 Widom",
  title =        "Human-assisted graph search: it's okay to ask
                 questions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "267--278",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yakout:2011:GDR,
  author =       "Mohamed Yakout and Ahmed K. Elmagarmid and Jennifer
                 Neville and Mourad Ouzzani and Ihab F. Ilyas",
  title =        "Guided data repair",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "279--289",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Venetis:2011:HLD,
  author =       "Petros Venetis and Hector Gonzalez and Christian S.
                 Jensen and Alon Halevy",
  title =        "Hyper-local, directions-based ranking of places",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "290--301",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Koc:2011:IMC,
  author =       "M. Levent Koc and Christopher R{\'e}",
  title =        "Incrementally maintaining classification using an
                 {RDBMS}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "302--313",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{He:2011:HTT,
  author =       "Bingsheng He and Jeffrey Xu Yu",
  title =        "High-throughput transaction executions on graphics
                 processors",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "314--325",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2011:DIQ,
  author =       "Zhao Cao and Charles Sutton and Yanlei Diao and
                 Prashant Shenoy",
  title =        "Distributed inference and query processing for {RFID}
                 tracking and monitoring",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "5",
  pages =        "326--337",
  month =        feb,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:55:18 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2011:SJS,
  author =       "Hongrae Lee and Raymond T. Ng and Kyuseok Shim",
  title =        "Similarity join size estimation using locality
                 sensitive hashing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "338--349",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2011:QEB,
  author =       "Ziyang Liu and Sivaramakrishnan Natarajan and Yi
                 Chen",
  title =        "Query expansion based on clustered results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "350--361",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dash:2011:CSP,
  author =       "Debabrata Dash and Neoklis Polyzotis and Anastasia
                 Ailamaki",
  title =        "{CoPhy}: a scalable, portable, and interactive index
                 advisor for large workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "362--372",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Niu:2011:TSS,
  author =       "Feng Niu and Christopher R{\'e} and AnHai Doan and
                 Jude Shavlik",
  title =        "{Tuffy}: scaling up statistical inference in {Markov}
                 logic networks using an {RDBMS}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "373--384",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jahani:2011:AOM,
  author =       "Eaman Jahani and Michael J. Cafarella and Christopher
                 R{\'e}",
  title =        "Automatic optimization for {MapReduce} programs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "385--396",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2011:STG,
  author =       "De-Nian Yang and Yi-Ling Chen and Wang-Chien Lee and
                 Ming-Syan Chen",
  title =        "On social-temporal group query with acquaintance
                 constraint",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "6",
  pages =        "397--408",
  month =        mar,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Fri May 13 14:45:07 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nguyen:2011:SPO,
  author =       "Hoa Nguyen and Ariel Fuxman and Stelios Paparizos and
                 Juliana Freire and Rakesh Agrawal",
  title =        "Synthesizing products for online catalogs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "409--418",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Floratou:2011:COS,
  author =       "Avrilia Floratou and Jignesh M. Patel and Eugene J.
                 Shekita and Sandeep Tata",
  title =        "Column-oriented storage techniques for {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "419--429",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lomet:2011:IPC,
  author =       "David Lomet and Kostas Tzoumas and Michael Zwilling",
  title =        "Implementing performance competitive logical
                 recovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "430--439",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Machanavajjhala:2011:PSR,
  author =       "Ashwin Machanavajjhala and Aleksandra Korolova and
                 Atish Das Sarma",
  title =        "Personalized social recommendations: accurate or
                 private",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "440--450",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Capannini:2011:EDW,
  author =       "Gabriele Capannini and Franco Maria Nardini and
                 Raffaele Perego and Fabrizio Silvestri",
  title =        "Efficient diversification of {Web} search results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "451--459",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{DeFrancisciMorales:2011:SCM,
  author =       "Gianmarco {De Francisci Morales} and Aristides Gionis
                 and Mauro Sozio",
  title =        "Social content matching in {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "7",
  pages =        "460--469",
  month =        apr,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Jun 7 19:31:12 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ao:2011:EPL,
  author =       "Naiyong Ao and Fan Zhang and Di Wu and Douglas S.
                 Stones and Gang Wang and Xiaoguang Liu and Jing Liu and
                 Sheng Lin",
  title =        "Efficient parallel lists intersection and index
                 compression algorithms using graphics processing
                 units",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "8",
  pages =        "470--481",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:33 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zou:2011:GAS,
  author =       "Lei Zou and Jinghui Mo and Lei Chen and M. Tamer
                 {\"O}zsu and Dongyan Zhao",
  title =        "{gStore}: answering {SPARQL} queries via subgraph
                 matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "8",
  pages =        "482--493",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:33 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Das:2011:ALE,
  author =       "Sudipto Das and Shoji Nishimura and Divyakant Agrawal
                 and Amr {El Abbadi}",
  title =        "{Albatross}: lightweight elasticity in shared storage
                 databases for the cloud using live data migration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "8",
  pages =        "494--505",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:33 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nutanong:2011:IHD,
  author =       "Sarana Nutanong and Edwin H. Jacox and Hanan Samet",
  title =        "An incremental {Hausdorff} distance calculation
                 algorithm",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "8",
  pages =        "506--517",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:33 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Blaustein:2011:SPP,
  author =       "Barbara Blaustein and Adriane Chapman and Len Seligman
                 and M. David Allen and Arnon Rosenthal",
  title =        "Surrogate parenthood: protected and informative
                 graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "8",
  pages =        "518--525",
  month =        may,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:33 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Venetis:2011:RST,
  author =       "Petros Venetis and Alon Halevy and Jayant Madhavan and
                 Marius Pasca and Warren Shen and Fei Wu and Gengxin
                 Miao and Chung Wu",
  title =        "Recovering semantics of tables on the web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "528--538",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Neumann:2011:ECE,
  author =       "Thomas Neumann",
  title =        "Efficiently compiling efficient query plans for modern
                 hardware",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "539--550",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jin:2011:DCR,
  author =       "Ruoming Jin and Lin Liu and Bolin Ding and Haixun
                 Wang",
  title =        "Distance-constraint reachability computation in
                 uncertain graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "551--562",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chi:2011:IIC,
  author =       "Yun Chi and Hyun Jin Moon and Hakan
                 Hacig{\"u}m{\"u}s",
  title =        "{iCBS}: incremental cost-based scheduling under
                 piecewise linear {SLAs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "563--574",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Eltabakh:2011:CFD,
  author =       "Mohamed Y. Eltabakh and Yuanyuan Tian and Fatma
                 {\"O}zcan and Rainer Gemulla and Aljoscha Krettek and
                 John McPherson",
  title =        "{CoHadoop}: flexible data placement and its
                 exploitation in {Hadoop}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "575--585",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Idreos:2011:MWC,
  author =       "Stratos Idreos and Stefan Manegold and Harumi Kuno and
                 Goetz Graefe",
  title =        "Merging what's cracked, cracking what's merged:
                 adaptive indexing in main-memory column-stores",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "9",
  pages =        "586--597",
  month =        jun,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2011:PTR,
  author =       "Chonghai Wang and Li Yan Yuan and Jia-Huai You and
                 Osmar R. Zaiane and Jian Pei",
  title =        "On pruning for top-$k$ ranking in uncertain
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "598--609",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pandis:2011:PPL,
  author =       "Ippokratis Pandis and Pinar T{\"o}z{\"u}n and Ryan
                 Johnson and Anastasia Ailamaki",
  title =        "{PLP}: page latch-free shared-everything {OLTP}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "610--621",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2011:EMH,
  author =       "Jiannan Wang and Guoliang Li and Jeffrey Xu Yu and
                 Jianhua Feng",
  title =        "Entity matching: how similar is similar",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "622--633",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2011:ACE,
  author =       "Di Wang and Elke A. Rundensteiner and Richard T.
                 {Ellison III}",
  title =        "Active complex event processing over event streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "634--645",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Budak:2011:STA,
  author =       "Ceren Budak and Divyakant Agrawal and Amr {El
                 Abbadi}",
  title =        "Structural trend analysis for online social networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "646--656",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kimura:2011:CAP,
  author =       "Hideaki Kimura and Vivek Narasayya and Manoj Syamala",
  title =        "Compression aware physical database design",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "657--668",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bernecker:2011:EPR,
  author =       "Thomas Bernecker and Tobias Emrich and Hans-Peter
                 Kriegel and Matthias Renz and Stefan Zankl and Andreas
                 Z{\"u}fle",
  title =        "Efficient probabilistic reverse nearest neighbor query
                 processing on uncertain data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "669--680",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kargar:2011:KSG,
  author =       "Mehdi Kargar and Aijun An",
  title =        "Keyword search in graphs: finding $r$-cliques",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "4",
  number =       "10",
  pages =        "681--692",
  month =        jul,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Mon Sep 5 17:23:34 MDT 2011",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fabbri:2011:EBA,
  author =       "Daniel Fabbri and Kristen LeFevre",
  title =        "Explanation-based auditing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "1--12",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "To comply with emerging privacy laws and regulations,
                 it has become common for applications like electronic
                 health records systems (EHRs) to collect access logs,
                 which record each time a user (e.g., a hospital
                 employee) accesses a piece of sensitive data (e.g., a
                 patient record). Using the access log, it is easy to
                 answer simple queries (e.g., Who accessed Alice's
                 medical record?), but this often does not provide
                 enough information. In addition to learning who
                 accessed their medical records, patients will likely
                 want to understand why each access occurred. In this
                 paper, we introduce the problem of generating
                 explanations for individual records in an access log.
                 The problem is motivated by user-centric auditing
                 applications, and it also provides a novel approach to
                 misuse detection. We develop a framework for modeling
                 explanations which is based on a fundamental
                 observation: For certain classes of databases,
                 including EHRs, the reason for most data accesses can
                 be inferred from data stored elsewhere in the database.
                 For example, if Alice has an appointment with Dr. Dave,
                 this information is stored in the database, and it
                 explains why Dr. Dave looked at Alice's record. Large
                 numbers of data accesses can be explained using general
                 forms called explanation templates. Rather than
                 requiring an administrator to manually specify
                 explanation templates, we propose a set of algorithms
                 for automatically discovering frequent templates from
                 the database (i.e., those that explain a large number
                 of accesses). We also propose techniques for inferring
                 collaborative user groups, which can be used to enhance
                 the quality of the discovered explanations. Finally, we
                 have evaluated our proposed techniques using an access
                 log and data from the University of Michigan Health
                 System. Our results demonstrate that in practice we can
                 provide explanations for over 94\% of data accesses in
                 the log.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Marcus:2011:HPS,
  author =       "Adam Marcus and Eugene Wu and David Karger and Samuel
                 Madden and Robert Miller",
  title =        "Human-powered sorts and joins",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "13--24",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Crowdsourcing markets like Amazon's Mechanical Turk
                 (MTurk) make it possible to task people with small
                 jobs, such as labeling images or looking up phone
                 numbers, via a programmatic interface. MTurk tasks for
                 processing datasets with humans are currently designed
                 with significant reimplementation of common workflows
                 and ad-hoc selection of parameters such as price to pay
                 per task. We describe how we have integrated crowds
                 into a declarative workflow engine called Qurk to
                 reduce the burden on workflow designers. In this paper,
                 we focus on how to use humans to compare items for
                 sorting and joining data, two of the most common
                 operations in DBMSs. We describe our basic query
                 interface and the user interface of the tasks we post
                 to MTurk. We also propose a number of optimizations,
                 including task batching, replacing pairwise comparisons
                 with numerical ratings, and pre-filtering tables before
                 joining them, which dramatically reduce the overall
                 cost of running sorts and joins on the crowd. In an
                 experiment joining two sets of images, we reduce the
                 overall cost from $67 in a naive implementation to
                 about $3, without substantially affecting accuracy or
                 latency. In an end-to-end experiment, we reduced cost
                 by a factor of 14.5.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cormode:2011:VCS,
  author =       "Graham Cormode and Justin Thaler and Ke Yi",
  title =        "Verifying computations with streaming interactive
                 proofs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "25--36",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "When computation is outsourced, the data owner would
                 like to be assured that the desired computation has
                 been performed correctly by the service provider. In
                 theory, proof systems can give the necessary assurance,
                 but prior work is not sufficiently scalable or
                 practical. In this paper, we develop new proof
                 protocols for verifying computations which are
                 streaming in nature: the verifier (data owner) needs
                 only logarithmic space and a single pass over the
                 input, and after observing the input follows a simple
                 protocol with a prover (service provider) that takes
                 logarithmic communication spread over a logarithmic
                 number of rounds. These ensure that the computation is
                 performed correctly: that the service provider has not
                 made any errors or missed out some data. The guarantee
                 is very strong: even if the service provider
                 deliberately tries to cheat, there is only vanishingly
                 small probability of doing so undetected, while a
                 correct computation is always accepted. We first
                 observe that some theoretical results can be modified
                 to work with streaming verifiers, showing that there
                 are efficient protocols for problems in the complexity
                 classes NP and NC. Our main results then seek to bridge
                 the gap between theory and practice by developing
                 usable protocols for a variety of problems of central
                 importance in streaming and database processing. All
                 these problems require linear space in the traditional
                 streaming model, and therefore our protocols
                 demonstrate that adding a prover can exponentially
                 reduce the effort needed by the verifier. Our
                 experimental results show that our protocols are
                 practical and scalable.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lin:2011:MOI,
  author =       "Dan Lin and Christian S. Jensen and Rui Zhang and Lu
                 Xiao and Jiaheng Lu",
  title =        "A moving-object index for efficient query processing
                 with peer-wise location privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "37--48",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "With the growing use of location-based services,
                 location privacy attracts increasing attention from
                 users, industry, and the research community. While
                 considerable effort has been devoted to inventing
                 techniques that prevent service providers from knowing
                 a user's exact location, relatively little attention
                 has been paid to enabling so-called peer-wise
                 privacy---the protection of a user's location from
                 unauthorized peer users. This paper identifies an
                 important efficiency problem in existing peer-privacy
                 approaches that simply apply a filtering step to
                 identify users that are located in a query range, but
                 that do not want to disclose their location to the
                 querying peer. To solve this problem, we propose a
                 novel, privacy-policy enabled index called the PEB-tree
                 that seamlessly integrates location proximity and
                 policy compatibility. We propose efficient algorithms
                 that use the PEB-tree for processing privacy-aware
                 range and $k$ NN queries. Extensive experiments suggest
                 that the PEB-tree enables efficient query processing.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mansour:2011:EES,
  author =       "Essam Mansour and Amin Allam and Spiros Skiadopoulos
                 and Panos Kalnis",
  title =        "{ERA}: efficient serial and parallel suffix tree
                 construction for very long strings",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "49--60",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The suffix tree is a data structure for indexing
                 strings. It is used in a variety of applications such
                 as bioinformatics, time series analysis, clustering,
                 text editing and data compression. However, when the
                 string and the resulting suffix tree are too large to
                 fit into the main memory, most existing construction
                 algorithms become very inefficient. This paper presents
                 a disk-based suffix tree construction method, called
                 Elastic Range (ERa), which works efficiently with very
                 long strings that are much larger than the available
                 memory. ERa partitions the tree construction process
                 horizontally and vertically and minimizes I/Os by
                 dynamically adjusting the horizontal partitions
                 independently for each vertical partition, based on the
                 evolving shape of the tree and the available memory.
                 Where appropriate, ERa also groups vertical partitions
                 together to amortize the I/O cost. We developed a
                 serial version; a parallel version for shared-memory
                 and shared-disk multi-core systems; and a parallel
                 version for shared-nothing architectures. ERa indexes
                 the entire human genome in 19 minutes on an ordinary
                 desktop computer. For comparison, the fastest existing
                 method needs 15 minutes using 1024 CPUs on an IBM
                 BlueGene supercomputer.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Krueger:2011:FUR,
  author =       "Jens Krueger and Changkyu Kim and Martin Grund and
                 Nadathur Satish and David Schwalb and Jatin Chhugani
                 and Hasso Plattner and Pradeep Dubey and Alexander
                 Zeier",
  title =        "Fast updates on read-optimized databases using
                 multi-core {CPUs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "61--72",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Read-optimized columnar databases use differential
                 updates to handle writes by maintaining a separate
                 write-optimized delta partition which is periodically
                 merged with the read-optimized and compressed main
                 partition. This merge process introduces significant
                 overheads and unacceptable downtimes in update
                 intensive systems, aspiring to combine transactional
                 and analytical workloads into one system. In the first
                 part of the paper, we report data analyses of 12 SAP
                 Business Suite customer systems. In the second half, we
                 present an optimized merge process reducing the merge
                 overhead of current systems by a factor of 30. Our
                 linear-time merge algorithm exploits the underlying
                 high compute and bandwidth resources of modern
                 multi-core CPUs with architecture-aware optimizations
                 and efficient parallelization. This enables compressed
                 in-memory column stores to handle the transactional
                 update rate required by enterprise applications, while
                 keeping properties of read-optimized databases for
                 analytic-style queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Goyal:2011:DBA,
  author =       "Amit Goyal and Francesco Bonchi and Laks V. S.
                 Lakshmanan",
  title =        "A data-based approach to social influence
                 maximization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "1",
  pages =        "73--84",
  month =        sep,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:06 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Influence maximization is the problem of finding a set
                 of users in a social network, such that by targeting
                 this set, one maximizes the expected spread of
                 influence in the network. Most of the literature on
                 this topic has focused exclusively on the social graph,
                 overlooking historical data, i.e., traces of past
                 action propagations. In this paper, we study influence
                 maximization from a novel data-based perspective. In
                 particular, we introduce a new model, which we call
                 credit distribution, that directly leverages available
                 propagation traces to learn how influence flows in the
                 network and uses this to estimate expected influence
                 spread. Our approach also learns the different levels
                 of influence-ability of users, and it is time-aware in
                 the sense that it takes the temporal nature of
                 influence into account. We show that influence
                 maximization under the credit distribution model is NP
                 -hard and that the function that defines expected
                 spread under our model is submodular. Based on these,
                 we develop an approximation algorithm for solving the
                 influence maximization problem that at once enjoys high
                 accuracy compared to the standard approach, while being
                 several orders of magnitude faster and more scalable.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pavlo:2011:PMO,
  author =       "Andrew Pavlo and Evan P. C. Jones and Stanley Zdonik",
  title =        "On predictive modeling for optimizing transaction
                 execution in parallel {OLTP} systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "85--96",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A new emerging class of parallel database management
                 systems (DBMS) is designed to take advantage of the
                 partitionable workloads of on-line transaction
                 processing (OLTP) applications [23, 20]. Transactions
                 in these systems are optimized to execute to completion
                 on a single node in a shared-nothing cluster without
                 needing to coordinate with other nodes or use expensive
                 concurrency control measures [18]. But some OLTP
                 applications cannot be partitioned such that all of
                 their transactions execute within a single-partition in
                 this manner. These distributed transactions access data
                 not stored within their local partitions and
                 subsequently require more heavy-weight concurrency
                 control protocols. Further difficulties arise when the
                 transaction's execution properties, such as the number
                 of partitions it may need to access or whether it will
                 abort, are not known beforehand. The DBMS could
                 mitigate these performance issues if it is provided
                 with additional information about transactions. Thus,
                 in this paper we present a Markov model-based approach
                 for automatically selecting which optimizations a DBMS
                 could use, namely (1) more efficient concurrency
                 control schemes, (2) intelligent scheduling, (3)
                 reduced undo logging, and (4) speculative execution. To
                 evaluate our techniques, we implemented our models and
                 integrated them into a parallel, main-memory OLTP DBMS
                 to show that we can improve the performance of
                 applications with diverse workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Goasdoue:2011:VSS,
  author =       "Fran{\c{c}}ois Goasdou{\'e} and Konstantinos Karanasos
                 and Julien Leblay and Ioana Manolescu",
  title =        "View selection in {Semantic Web} databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "97--108",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We consider the setting of a Semantic Web database,
                 containing both explicit data encoded in RDF triples,
                 and implicit data, implied by the RDF semantics. Based
                 on a query workload, we address the problem of
                 selecting a set of views to be materialized in the
                 database, minimizing a combination of query processing,
                 view storage, and view maintenance costs. Starting from
                 an existing relational view selection method, we devise
                 new algorithms for recommending view sets, and show
                 that they scale significantly beyond the existing
                 relational ones when adapted to the RDF context. To
                 account for implicit triples in query answers, we
                 propose a novel RDF query reformulation algorithm and
                 an innovative way of incorporating it into view
                 selection in order to avoid a combinatorial explosion
                 in the complexity of the selection process. The
                 interest of our techniques is demonstrated through a
                 set of experiments.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jestes:2011:BWH,
  author =       "Jeffrey Jestes and Ke Yi and Feifei Li",
  title =        "Building wavelet histograms on large data in
                 {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "109--120",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "MapReduce is becoming the de facto framework for
                 storing and processing massive data, due to its
                 excellent scalability, reliability, and elasticity. In
                 many MapReduce applications, obtaining a compact
                 accurate summary of data is essential. Among various
                 data summarization tools, histograms have proven to be
                 particularly important and useful for summarizing data,
                 and the wavelet histogram is one of the most widely
                 used histograms. In this paper, we investigate the
                 problem of building wavelet histograms efficiently on
                 large datasets in MapReduce. We measure the efficiency
                 of the algorithms by both end-to-end running time and
                 communication cost. We demonstrate straightforward
                 adaptations of existing exact and approximate methods
                 for building wavelet histograms to MapReduce clusters
                 are highly inefficient. To that end, we design new
                 algorithms for computing exact and approximate wavelet
                 histograms and discuss their implementation in
                 MapReduce. We illustrate our techniques in Hadoop, and
                 compare to baseline solutions with extensive
                 experiments performed in a heterogeneous Hadoop cluster
                 of 16 nodes, using large real and synthetic datasets,
                 up to hundreds of gigabytes. The results suggest
                 significant (often orders of magnitude) performance
                 improvement achieved by our new algorithms.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2011:SMD,
  author =       "Di Yang and Elke A. Rundensteiner and Matthew O.
                 Ward",
  title =        "Summarization and matching of density-based clusters
                 in streaming environments",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "121--132",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Density-based cluster mining is known to serve a broad
                 range of applications ranging from stock trade analysis
                 to moving object monitoring. Although methods for
                 efficient extraction of density-based clusters have
                 been studied in the literature, the problem of
                 summarizing and matching of such clusters with
                 arbitrary shapes and complex cluster structures remains
                 unsolved. Therefore, the goal of our work is to extend
                 the state-of-art of density-based cluster mining in
                 streams from cluster extraction only to now also
                 support analysis and management of the extracted
                 clusters. Our work solves three major technical
                 challenges. First, we propose a novel multi-resolution
                 cluster summarization method, called Skeletal Grid
                 Summarization (SGS), which captures the key features of
                 density-based clusters, covering both their external
                 shape and internal cluster structures. Second, in order
                 to summarize the extracted clusters in real-time, we
                 present an integrated computation strategy C-SGS, which
                 piggybacks the generation of cluster summarizations
                 within the online clustering process. Lastly, we design
                 a mechanism to efficiently execute cluster matching
                 queries, which identify similar clusters for given
                 cluster of analyst's interest from clusters extracted
                 earlier in the stream history. Our experimental study
                 using real streaming data shows the clear superiority
                 of our proposed methods in both efficiency and
                 effectiveness for cluster summarization and cluster
                 matching queries to other potential alternatives.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nguyen:2011:MSM,
  author =       "Thanh Nguyen and Viviane Moreira and Huong Nguyen and
                 Hoa Nguyen and Juliana Freire",
  title =        "Multilingual schema matching for {Wikipedia}
                 infoboxes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "133--144",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Recent research has taken advantage of Wikipedia's
                 multi-lingualism as a resource for cross-language
                 information retrieval and machine translation, as well
                 as proposed techniques for enriching its cross-language
                 structure. The availability of documents in multiple
                 languages also opens up new opportunities for querying
                 structured Wikipedia content, and in particular, to
                 enable answers that straddle different languages. As a
                 step towards supporting such queries, in this paper, we
                 propose a method for identifying mappings between
                 attributes from infoboxes that come from pages in
                 different languages. Our approach finds mappings in a
                 completely automated fashion. Because it does not
                 require training data, it is scalable: not only can it
                 be used to find mappings between many language pairs,
                 but it is also effective for languages that are
                 under-represented and lack sufficient training samples.
                 Another important benefit of our approach is that it
                 does not depend on syntactic similarity between
                 attribute names, and thus, it can be applied to
                 language pairs that have distinct morphologies. We have
                 performed an extensive experimental evaluation using a
                 corpus consisting of pages in Portuguese, Vietnamese,
                 and English. The results show that not only does our
                 approach obtain high precision and recall, but it also
                 outperforms state-of-the-art techniques. We also
                 present a case study which demonstrates that the
                 multilingual mappings we derive lead to substantial
                 improvements in answer quality and coverage for
                 structured queries over Wikipedia content.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2011:CFP,
  author =       "Guimei Liu and Haojun Zhang and Limsoon Wong",
  title =        "Controlling false positives in association rule
                 mining",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "2",
  pages =        "145--156",
  month =        oct,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:08 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Association rule mining is an important problem in the
                 data mining area. It enumerates and tests a large
                 number of rules on a dataset and outputs rules that
                 satisfy user-specified constraints. Due to the large
                 number of rules being tested, rules that do not
                 represent real systematic effect in the data can
                 satisfy the given constraints purely by random chance.
                 Hence association rule mining often suffers from a high
                 risk of false positive errors. There is a lack of
                 comprehensive study on controlling false positives in
                 association rule mining. In this paper, we adopt three
                 multiple testing correction approaches---the direct
                 adjustment approach, the permutation-based approach and
                 the holdout approach---to control false positives in
                 association rule mining, and conduct extensive
                 experiments to study their performance. Our results
                 show that (1) Numerous spurious rules are generated if
                 no correction is made. (2) The three approaches can
                 control false positives effectively. Among the three
                 approaches, the permutation-based approach has the
                 highest power of detecting real association rules, but
                 it is very computationally expensive. We employ several
                 techniques to reduce its cost effectively.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Suchanek:2011:PPA,
  author =       "Fabian M. Suchanek and Serge Abiteboul and Pierre
                 Senellart",
  title =        "{PARIS}: probabilistic alignment of relations,
                 instances, and schema",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "157--168",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "One of the main challenges that the Semantic Web faces
                 is the integration of a growing number of independently
                 designed ontologies. In this work, we present paris, an
                 approach for the automatic alignment of ontologies.
                 paris aligns not only instances, but also relations and
                 classes. Alignments at the instance level
                 cross-fertilize with alignments at the schema level.
                 Thereby, our system provides a truly holistic solution
                 to the problem of ontology alignment. The heart of the
                 approach is probabilistic, i.e., we measure degrees of
                 matchings based on probability estimates. This allows
                 paris to run without any parameter tuning. We
                 demonstrate the efficiency of the algorithm and its
                 precision through extensive experiments. In particular,
                 we obtain a precision of around 90\% in experiments
                 with some of the world's largest ontologies.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ranu:2011:ATQ,
  author =       "Sayan Ranu and Ambuj K. Singh",
  title =        "Answering top-$k$ queries over a mixture of attractive
                 and repulsive dimensions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "169--180",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this paper, we formulate a top-$k$ query that
                 compares objects in a database to a user-provided query
                 object on a novel scoring function. The proposed
                 scoring function combines the idea of attractive and
                 repulsive dimensions into a general framework to
                 overcome the weakness of traditional distance or
                 similarity measures. We study the properties of the
                 proposed class of scoring functions and develop
                 efficient and scalable index structures that index the
                 isolines of the function. We demonstrate various
                 scenarios where the query finds application. Empirical
                 evaluation demonstrates a performance gain of one to
                 two orders of magnitude on querying time over existing
                 state-of-the-art top-$k$ techniques. Further, a
                 qualitative analysis is performed on a real dataset to
                 highlight the potential of the proposed query in
                 discovering hidden data characteristics.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Armbrust:2011:PST,
  author =       "Michael Armbrust and Kristal Curtis and Tim Kraska and
                 Armando Fox and Michael J. Franklin and David A.
                 Patterson",
  title =        "{PIQL}: success-tolerant query processing in the
                 cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "181--192",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Newly-released web applications often succumb to a
                 ``Success Disaster,'' where overloaded database
                 machines and resulting high response times destroy a
                 previously good user experience. Unfortunately, the
                 data independence provided by a traditional relational
                 database system, while useful for agile development,
                 only exacerbates the problem by hiding potentially
                 expensive queries under simple declarative expressions.
                 As a result, developers of these applications are
                 increasingly abandoning relational databases in favor
                 of imperative code written against distributed
                 key/value stores, losing the many benefits of data
                 independence in the process. Instead, we propose PIQL,
                 a declarative language that also provides scale
                 independence by calculating an upper bound on the
                 number of key/value store operations that will be
                 performed for any query. Coupled with a service level
                 objective (SLO) compliance prediction model and PIQL's
                 scalable database architecture, these bounds make it
                 easy for developers to write success-tolerant
                 applications that support an arbitrarily large number
                 of users while still providing acceptable performance.
                 In this paper, we present the PIQL query processing
                 system and evaluate its scale independence on hundreds
                 of machines using two benchmarks, TPC-W and SCADr.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhao:2011:GQE,
  author =       "Peixiang Zhao and Charu C. Aggarwal and Min Wang",
  title =        "{gSketch}: on query estimation in graph streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "193--204",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Many dynamic applications are built upon large network
                 infrastructures, such as social networks, communication
                 networks, biological networks and the Web. Such
                 applications create data that can be naturally modeled
                 as graph streams, in which edges of the underlying
                 graph are received and updated sequentially in a form
                 of a stream. It is often necessary and important to
                 summarize the behavior of graph streams in order to
                 enable effective query processing. However, the sheer
                 size and dynamic nature of graph streams present an
                 enormous challenge to existing graph management
                 techniques. In this paper, we propose a new graph
                 sketch method, gSketch, which combines well studied
                 synopses for traditional data streams with a sketch
                 partitioning technique, to estimate and optimize the
                 responses to basic queries on graph streams. We
                 consider two different scenarios for query estimation:
                 (1) A graph stream sample is available; (2) Both a
                 graph stream sample and a query workload sample are
                 available. Algorithms for different scenarios are
                 designed respectively by partitioning a global sketch
                 to a group of localized sketches in order to optimize
                 the query estimation accuracy. We perform extensive
                 experimental studies on both real and synthetic data
                 sets and demonstrate the power and robustness of
                 gSketch in comparison with the state-of-the-art global
                 sketch method.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ruttenberg:2011:IEM,
  author =       "Brian E. Ruttenberg and Ambuj K. Singh",
  title =        "Indexing the earth mover's distance using normal
                 distributions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "205--216",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Querying uncertain data sets (represented as
                 probability distributions) presents many challenges due
                 to the large amount of data involved and the
                 difficulties comparing uncertainty between
                 distributions. The Earth Mover's Distance (EMD) has
                 increasingly been employed to compare uncertain data
                 due to its ability to effectively capture the
                 differences between two distributions. Computing the
                 EMD entails finding a solution to the transportation
                 problem, which is computationally intensive. In this
                 paper, we propose a new lower bound to the EMD and an
                 index structure to significantly improve the
                 performance of EMD based K-- nearest neighbor (K--NN)
                 queries on uncertain databases. We propose a new lower
                 bound to the EMD that approximates the EMD on a
                 projection vector. Each distribution is projected onto
                 a vector and approximated by a normal distribution, as
                 well as an accompanying error term. We then represent
                 each normal as a point in a Hough transformed space. We
                 then use the concept of stochastic dominance to
                 implement an efficient index structure in the
                 transformed space. We show that our method
                 significantly decreases K--NN query time on uncertain
                 databases. The index structure also scales well with
                 database cardinality. It is well suited for
                 heterogeneous data sets, helping to keep EMD based
                 queries tractable as uncertain data sets become larger
                 and more complex.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Qumsiyeh:2011:GER,
  author =       "Rani Qumsiyeh and Maria S. Pera and Yiu-Kai Ng",
  title =        "Generating exact- and ranked partially-matched answers
                 to questions in advertisements",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "217--228",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Taking advantage of the Web, many advertisements (ads
                 for short) websites, which aspire to increase client's
                 transactions and thus profits, offer searching tools
                 which allow users to (i) post keyword queries to
                 capture their information needs or (ii) invoke
                 form-based interfaces to create queries by selecting
                 search options, such as a price range, filled-in
                 entries, check boxes, or drop-down menus. These search
                 mechanisms, however, are inadequate, since they cannot
                 be used to specify a natural-language query with rich
                 syntactic and semantic content, which can only be
                 handled by a question answering (QA) system.
                 Furthermore, existing ads websites are incapable of
                 evaluating arbitrary Boolean queries or retrieving
                 partially-matched answers that might be of interest to
                 the user whenever a user's search yields only a few or
                 no results at all. In solving these problems, we
                 present a QA system for ads, called CQAds, which (i)
                 allows users to post a natural-language question Q for
                 retrieving relevant ads, if they exist, (ii) identifies
                 ads as answers that partially-match the requested
                 information expressed in Q, if insufficient or no
                 answers to Q can be retrieved, which are ordered using
                 a similarity-ranking approach, and (iii) analyzes
                 incomplete or ambiguous questions to perform the ``best
                 guess'' in retrieving answers that ``best match'' the
                 selection criteria specified in Q. CQAds is also
                 equipped with a Boolean model to evaluate Boolean
                 operators that are either explicitly or implicitly
                 specified in Q, i.e., with or without Boolean operators
                 specified by the users, respectively. CQAds is easy to
                 use, scalable to all ads domains, and more powerful
                 than search tools provided by existing ads websites,
                 since its query-processing strategy retrieves relevant
                 ads of higher quality and quantity. We have verified
                 the accuracy of CQAds in retrieving ads on eight ads
                 domains and compared its ranking strategy with other
                 well-known ranking approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fakas:2011:SOS,
  author =       "Georgios J. Fakas and Zhi Cai and Nikos Mamoulis",
  title =        "Size-$l$ object summaries for relational keyword
                 search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "229--240",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A previously proposed keyword search paradigm
                 produces, as a query result, a ranked list of Object
                 Summaries (OSs). An OS is a tree structure of related
                 tuples that summarizes all data held in a relational
                 database about a particular Data Subject (DS). However,
                 some of these OSs are very large in size and therefore
                 unfriendly to users that initially prefer synoptic
                 information before proceeding to more comprehensive
                 information about a particular DS. In this paper, we
                 investigate the effective and efficient retrieval of
                 concise and informative OSs. We argue that a good size-
                 l OS should be a stand-alone and meaningful synopsis of
                 the most important information about the particular DS.
                 More precisely, we define a size- l OS as a partial OS
                 composed of l important tuples. We propose three
                 algorithms for the efficient generation of size- l OSs
                 (in addition to the optimal approach which requires
                 exponential time). Experimental evaluation on DBLP and
                 TPC-H databases verifies the effectiveness and
                 efficiency of our approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fang:2011:RER,
  author =       "Lujun Fang and Anish Das Sarma and Cong Yu and Philip
                 Bohannon",
  title =        "{REX}: explaining relationships between entity pairs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "241--252",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Knowledge bases of entities and relations (either
                 constructed manually or automatically) are behind many
                 real world search engines, including those at Yahoo!,
                 Microsoft, and Google. Those knowledge bases can be
                 viewed as graphs with nodes representing entities and
                 edges representing (primary) relationships, and various
                 studies have been conducted on how to leverage them to
                 answer entity seeking queries. Meanwhile, in a
                 complementary direction, analyses over the query logs
                 have enabled researchers to identify entity pairs that
                 are statistically correlated. Such entity relationships
                 are then presented to search users through the
                 ``related searches'' feature in modern search engines.
                 However, entity relationships thus discovered can often
                 be ``puzzling'' to the users because why the entities
                 are connected is often indescribable. In this paper, we
                 propose a novel problem called entity relationship
                 explanation, which seeks to explain why a pair of
                 entities are connected, and solve this challenging
                 problem by integrating the above two complementary
                 approaches, i.e., we leverage the knowledge base to
                 ``explain'' the connections discovered between entity
                 pairs. More specifically, we present REX, a system that
                 takes a pair of entities in a given knowledge base as
                 input and efficiently identifies a ranked list of
                 relationship explanations. We formally define
                 relationship explanations and analyze their desirable
                 properties. Furthermore, we design and implement
                 algorithms to efficiently enumerate and rank all
                 relationship explanations based on multiple measures of
                 ``interestingness.'' We perform extensive experiments
                 over real web-scale data gathered from DBpedia and a
                 commercial search engine, demonstrating the efficiency
                 and scalability of REX. We also perform user studies to
                 corroborate the effectiveness of explanations generated
                 by REX.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2011:PJP,
  author =       "Guoliang Li and Dong Deng and Jiannan Wang and Jianhua
                 Feng",
  title =        "Pass-join: a partition-based method for similarity
                 joins",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "253--264",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As an essential operation in data cleaning, the
                 similarity join has attracted considerable attention
                 from the database community. In this paper, we study
                 string similarity joins with edit-distance constraints,
                 which find similar string pairs from two large sets of
                 strings whose edit distance is within a given
                 threshold. Existing algorithms are efficient either for
                 short strings or for long strings, and there is no
                 algorithm that can efficiently and adaptively support
                 both short strings and long strings. To address this
                 problem, we propose a partition-based method called
                 Pass-Join. Pass-Join partitions a string into a set of
                 segments and creates inverted indices for the segments.
                 Then for each string, Pass-Join selects some of its
                 substrings and uses the selected substrings to find
                 candidate pairs using the inverted indices. We devise
                 efficient techniques to select the substrings and prove
                 that our method can minimize the number of selected
                 substrings. We develop novel pruning techniques to
                 efficiently verify the candidate pairs. Experimental
                 results show that our algorithms are efficient for both
                 short strings and long strings, and outperform
                 state-of-the-art methods on real datasets.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hoobin:2011:RLZ,
  author =       "Christopher Hoobin and Simon J. Puglisi and Justin
                 Zobel",
  title =        "Relative {Lempel--Ziv} factorization for efficient
                 storage and retrieval of {Web} collections",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "3",
  pages =        "265--273",
  month =        nov,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:09 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Compression techniques that support fast random access
                 are a core component of any information system. Current
                 state-of-the-art methods group documents into
                 fixed-sized blocks and compress each block with a
                 general-purpose adaptive algorithm such as gzip. Random
                 access to a specific document then requires
                 decompression of a block. The choice of block size is
                 critical: it trades between compression effectiveness
                 and document retrieval times. In this paper we present
                 a scalable compression method for large document
                 collections that allows fast random access. We build a
                 representative sample of the collection and use it as a
                 dictionary in a LZ77-like encoding of the rest of the
                 collection, relative to the dictionary. We demonstrate
                 on large collections, that using a dictionary as small
                 as 0.1\% of the collection size, our algorithm is
                 dramatically faster than previous methods, and in
                 general gives much better compression.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2011:TCE,
  author =       "Ning Zhang and Junichi Tatemura and Jignesh M. Patel
                 and Hakan Hacig{\"u}m{\"u}s",
  title =        "Towards cost-effective storage provisioning for
                 {DBMSs}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "274--285",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Data center operators face a bewildering set of
                 choices when considering how to provision resources on
                 machines with complex I/O subsystems. Modern I/O
                 subsystems often have a rich mix of fast, high
                 performing, but expensive SSDs sitting alongside with
                 cheaper but relatively slower (for random accesses)
                 traditional hard disk drives. The data center operators
                 need to determine how to provision the I/O resources
                 for specific workloads so as to abide by existing
                 Service Level Agreements (SLAs), while minimizing the
                 total operating cost (TOC) of running the workload,
                 where the TOC includes the amortized hardware costs and
                 the run time energy costs. The focus of this paper is
                 on introducing this new problem of TOC-based storage
                 allocation, cast in a framework that is compatible with
                 traditional DBMS query optimization and query
                 processing architecture. We also present a
                 heuristic-based solution to this problem, called DOT.
                 We have implemented DOT in PostgreSQL, and experiments
                 using TPC-H and TPC-C demonstrate significant TOC
                 reduction by DOT in various settings.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Roh:2011:BTI,
  author =       "Hongchan Roh and Sanghyun Park and Sungho Kim and
                 Mincheol Shin and Sang-Won Lee",
  title =        "{B+}-tree index optimization by exploiting internal
                 parallelism of flash-based solid state drives",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "286--297",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Previous research addressed the potential problems of
                 the hard-disk oriented design of DBMSs of flashSSDs. In
                 this paper, we focus on exploiting potential benefits
                 of flashSSDs. First, we examine the internal
                 parallelism issues of flashSSDs by conducting
                 benchmarks to various flashSSDs. Then, we suggest
                 algorithm-design principles in order to best benefit
                 from the internal parallelism. We present a new I/O
                 request concept, called psync I/O that can exploit the
                 internal parallelism of flashSSDs in a single process.
                 Based on these ideas, we introduce B+-tree optimization
                 methods in order to utilize internal parallelism. By
                 integrating the results of these methods, we present a
                 B+-tree variant, PIO B-tree. We confirmed that each
                 optimization method substantially enhances the index
                 performance. Consequently, PIO B-tree enhanced
                 B+-tree's insert performance by a factor of up to 16.3,
                 while improving point-search performance by a factor of
                 1.2. The range search of PIO B-tree was up to 5 times
                 faster than that of the B+-tree. Moreover, PIO B-tree
                 outperformed other flash-aware indexes in various
                 synthetic workloads. We also confirmed that PIO B-tree
                 outperforms B+-tree in index traces collected inside
                 the PostgreSQL DBMS with TPC-C benchmark.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Larson:2011:HPC,
  author =       "Per-{\AA}ke Larson and Spyros Blanas and Cristian
                 Diaconu and Craig Freedman and Jignesh M. Patel and
                 Mike Zwilling",
  title =        "High-performance concurrency control mechanisms for
                 main-memory databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "298--309",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A database system optimized for in-memory storage can
                 support much higher transaction rates than current
                 systems. However, standard concurrency control methods
                 used today do not scale to the high transaction rates
                 achievable by such systems. In this paper we introduce
                 two efficient concurrency control methods specifically
                 designed for main-memory databases. Both use
                 multiversioning to isolate read-only transactions from
                 updates but differ in how atomicity is ensured: one is
                 optimistic and one is pessimistic. To avoid expensive
                 context switching, transactions never block during
                 normal processing but they may have to wait before
                 commit to ensure correct serialization ordering. We
                 also implemented a main-memory optimized version of
                 single-version locking. Experimental results show that
                 while single-version locking works well when
                 transactions are short and contention is low
                 performance degrades under more demanding conditions.
                 The multiversion schemes have higher overhead but are
                 much less sensitive to hotspots and the presence of
                 long-running transactions.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ma:2011:CTG,
  author =       "Shuai Ma and Yang Cao and Wenfei Fan and Jinpeng Huai
                 and Tianyu Wo",
  title =        "Capturing topology in graph pattern matching",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "310--321",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Graph pattern matching is often defined in terms of
                 subgraph isomorphism, an np-complete problem. To lower
                 its complexity, various extensions of graph simulation
                 have been considered instead. These extensions allow
                 pattern matching to be conducted in cubic-time.
                 However, they fall short of capturing the topology of
                 data graphs, i.e., graphs may have a structure
                 drastically different from pattern graphs they match,
                 and the matches found are often too large to understand
                 and analyze. To rectify these problems, this paper
                 proposes a notion of strong simulation, a revision of
                 graph simulation, for graph pattern matching. (1) We
                 identify a set of criteria for preserving the topology
                 of graphs matched. We show that strong simulation
                 preserves the topology of data graphs and finds a
                 bounded number of matches. (2) We show that strong
                 simulation retains the same complexity as earlier
                 extensions of simulation, by providing a cubic-time
                 algorithm for computing strong simulation. (3) We
                 present the locality property of strong simulation,
                 which allows us to effectively conduct pattern matching
                 on distributed graphs. (4) We experimentally verify the
                 effectiveness and efficiency of these algorithms, using
                 real-life data and synthetic data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kumar:2011:PMO,
  author =       "Arun Kumar and Christopher R{\'e}",
  title =        "Probabilistic management of {OCR} data using an
                 {RDBMS}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "322--333",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The digitization of scanned forms and documents is
                 changing the data sources that enterprises manage. To
                 integrate these new data sources with enterprise data,
                 the current state-of-the-art approach is to convert the
                 images to ASCII text using optical character
                 recognition (OCR) software and then to store the
                 resulting ASCII text in a relational database. The OCR
                 problem is challenging, and so the output of OCR often
                 contains errors. In turn, queries on the output of OCR
                 may fail to retrieve relevant answers. State-of-the-art
                 OCR programs, e.g., the OCR powering Google Books, use
                 a probabilistic model that captures many alternatives
                 during the OCR process. Only when the results of OCR
                 are stored in the database, do these approaches discard
                 the uncertainty. In this work, we propose to retain the
                 probabilistic models produced by OCR process in a
                 relational database management system. A key technical
                 challenge is that the probabilistic data produced by
                 OCR software is very large (a single book blows up to
                 2GB from 400kB as ASCII). As a result, a baseline
                 solution that integrates these models with an RDBMS is
                 over 1000x slower versus standard text processing for
                 single table select-project queries. However, many
                 applications may have quality-performance needs that
                 are in between these two extremes of ASCII and the
                 complete model output by the OCR software. Thus, we
                 propose a novel approximation scheme called Staccato
                 that allows a user to trade recall for query
                 performance. Additionally, we provide a formal analysis
                 of our scheme's properties, and describe how we
                 integrate our scheme with standard-RDBMS text
                 indexing.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pawlik:2011:RRA,
  author =       "Mateusz Pawlik and Nikolaus Augsten",
  title =        "{RTED}: a robust algorithm for the tree edit
                 distance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "334--345",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We consider the classical tree edit distance between
                 ordered labeled trees, which is defined as the
                 minimum-cost sequence of node edit operations that
                 transform one tree into another. The state-of-the-art
                 solutions for the tree edit distance are not
                 satisfactory. The main competitors in the field either
                 have optimal worst-case complexity, but the worst case
                 happens frequently, or they are very efficient for some
                 tree shapes, but degenerate for others. This leads to
                 unpredictable and often infeasible runtimes. There is
                 no obvious way to choose between the algorithms. In
                 this paper we present RTED, a robust tree edit distance
                 algorithm. The asymptotic complexity of RTED is smaller
                 or equal to the complexity of the best competitors for
                 any input instance, i.e., RTED is both efficient and
                 worst-case optimal. We introduce the class of LRH
                 (Left-Right-Heavy) algorithms, which includes RTED and
                 the fastest tree edit distance algorithms presented in
                 literature. We prove that RTED outperforms all
                 previously proposed LRH algorithms in terms of runtime
                 complexity. In our experiments on synthetic and real
                 world data we empirically evaluate our solution and
                 compare it to the state-of-the-art.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Amsterdamer:2011:PLP,
  author =       "Yael Amsterdamer and Susan B. Davidson and Daniel
                 Deutch and Tova Milo and Julia Stoyanovich and Val
                 Tannen",
  title =        "Putting lipstick on pig: enabling database-style
                 workflow provenance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "346--357",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Workflow provenance typically assumes that each module
                 is a ``black-box'', so that each output depends on all
                 inputs (coarse-grained dependencies). Furthermore, it
                 does not model the internal state of a module, which
                 can change between repeated executions. In practice,
                 however, an output may depend on only a small subset of
                 the inputs (fine-grained dependencies) as well as on
                 the internal state of the module. We present a novel
                 provenance framework that marries database-style and
                 workflow-style provenance, by using Pig Latin to expose
                 the functionality of modules, thus capturing internal
                 state and fine-grained dependencies. A critical
                 ingredient in our solution is the use of a novel form
                 of provenance graph that models module invocations and
                 yields a compact representation of fine-grained
                 workflow provenance. It also enables a number of novel
                 graph transformation operations, allowing to choose the
                 desired level of granularity in provenance querying
                 (ZoomIn and ZoomOut), and supporting ``what-if''
                 workflow analytic queries. We implemented our approach
                 in the Lipstick system and developed a benchmark in
                 support of a systematic performance evaluation. Our
                 results demonstrate the feasibility of tracking and
                 querying fine-grained workflow provenance.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gao:2011:RAS,
  author =       "Jun Gao and Ruoming Jin and Jiashuai Zhou and Jeffrey
                 Xu Yu and Xiao Jiang and Tengjiao Wang",
  title =        "Relational approach for shortest path discovery over
                 large graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "358--369",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "With the rapid growth of large graphs, we cannot
                 assume that graphs can still be fully loaded into
                 memory, thus the disk-based graph operation is
                 inevitable. In this paper, we take the shortest path
                 discovery as an example to investigate the technique
                 issues when leveraging existing infrastructure of
                 relational database (RDB) in the graph data management.
                 Based on the observation that a variety of graph search
                 queries can be implemented by iterative operations
                 including selecting frontier nodes from visited nodes,
                 making expansion from the selected frontier nodes, and
                 merging the expanded nodes into the visited ones, we
                 introduce a relational FEM framework with three
                 corresponding operators to implement graph search tasks
                 in the RDB context. We show new features such as window
                 function and merge statement introduced by recent SQL
                 standards can not only simplify the expression but also
                 improve the performance of the FEM framework. In
                 addition, we propose two optimization strategies
                 specific to shortest path discovery inside the FEM
                 framework. First, we take a bi-directional set
                 Dijkstra's algorithm in the path finding. The
                 bi-directional strategy can reduce the search space,
                 and set Dijkstra's algorithm finds the shortest path in
                 a set-at-a-time fashion. Second, we introduce an index
                 named SegTable to preserve the local shortest segments,
                 and exploit SegTable to further improve the
                 performance. The final extensive experimental results
                 illustrate our relational approach with the
                 optimization strategies achieves high scalability and
                 performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Barsky:2011:MFC,
  author =       "Marina Barsky and Sangkyum Kim and Tim Weninger and
                 Jiawei Han",
  title =        "Mining flipping correlations from large datasets with
                 taxonomies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "370--381",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this paper we introduce a new type of pattern --- a
                 flipping correlation pattern. The flipping patterns are
                 obtained from contrasting the correlations between
                 items at different levels of abstraction. They
                 represent surprising correlations, both positive and
                 negative, which are specific for a given abstraction
                 level, and which ``flip'' from positive to negative and
                 vice versa when items are generalized to a higher level
                 of abstraction. We design an efficient algorithm for
                 finding flipping correlations, the Flipper algorithm,
                 which outperforms na{\"\i}ve pattern mining methods by
                 several orders of magnitude. We apply Flipper to
                 real-life datasets and show that the discovered
                 patterns are non-redundant, surprising and actionable.
                 Flipper finds strong contrasting correlations in
                 itemsets with low-to-medium support, while existing
                 techniques cannot handle the pattern discovery in this
                 frequency range.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Konig:2011:SAT,
  author =       "Arnd Christian K{\"o}nig and Bolin Ding and Surajit
                 Chaudhuri and Vivek Narasayya",
  title =        "A statistical approach towards robust progress
                 estimation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "4",
  pages =        "382--393",
  month =        dec,
  year =         "2011",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:11 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The need for accurate SQL progress estimation in the
                 context of decision support administration has led to a
                 number of techniques proposed for this task.
                 Unfortunately, no single one of these progress
                 estimators behaves robustly across the variety of SQL
                 queries encountered in practice, meaning that each
                 technique performs poorly for a significant fraction of
                 queries. This paper proposes a novel estimator
                 selection framework that uses a statistical model to
                 characterize the sets of conditions under which certain
                 estimators outperform others, leading to a significant
                 increase in estimation robustness. The generality of
                 this framework also enables us to add a number of novel
                 ``special purpose'' estimators which increase accuracy
                 further. Most importantly, the resulting model
                 generalizes well to queries very different from the
                 ones used to train it. We validate our findings using a
                 large number of industrial real-life and benchmark
                 workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sun:2012:RSA,
  author =       "Yizhou Sun and Charu C. Aggarwal and Jiawei Han",
  title =        "Relation strength-aware clustering of heterogeneous
                 information networks with incomplete attributes",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "394--405",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "With the rapid development of online social media,
                 online shopping sites and cyber-physical systems,
                 heterogeneous information networks have become
                 increasingly popular and content-rich over time. In
                 many cases, such networks contain multiple types of
                 objects and links, as well as different kinds of
                 attributes. The clustering of these objects can provide
                 useful insights in many applications. However, the
                 clustering of such networks can be challenging since
                 (a) the attribute values of objects are often
                 incomplete, which implies that an object may carry only
                 partial attributes or even no attributes to correctly
                 label itself; and (b) the links of different types may
                 carry different kinds of semantic meanings, and it is a
                 difficult task to determine the nature of their
                 relative importance in helping the clustering for a
                 given purpose. In this paper, we address these
                 challenges by proposing a model-based clustering
                 algorithm. We design a probabilistic model which
                 clusters the objects of different types into a common
                 hidden space, by using a user-specified set of
                 attributes, as well as the links from different
                 relations. The strengths of different types of links
                 are automatically learned, and are determined by the
                 given purpose of clustering. An iterative algorithm is
                 designed for solving the clustering problem, in which
                 the strengths of different types of links and the
                 quality of clustering results mutually enhance each
                 other. Our experimental results on real and synthetic
                 data sets demonstrate the effectiveness and efficiency
                 of the algorithm.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2012:SPD,
  author =       "Lingkun Wu and Xiaokui Xiao and Dingxiong Deng and Gao
                 Cong and Andy Diwen Zhu and Shuigeng Zhou",
  title =        "Shortest path and distance queries on road networks:
                 an experimental evaluation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "406--417",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Computing the shortest path between two given
                 locations in a road network is an important problem
                 that finds applications in various map services and
                 commercial navigation products. The state-of-the-art
                 solutions for the problem can be divided into two
                 categories: spatial-coherence-based methods and
                 vertex-importance-based approaches. The two categories
                 of techniques, however, have not been compared
                 systematically under the same experimental framework,
                 as they were developed from two independent lines of
                 research that do not refer to each other. This renders
                 it difficult for a practitioner to decide which
                 technique should be adopted for a specific application.
                 Furthermore, the experimental evaluation of the
                 existing techniques, as presented in previous work,
                 falls short in several aspects. Some methods were
                 tested only on small road networks with up to one
                 hundred thousand vertices; some approaches were
                 evaluated using distance queries (instead of shortest
                 path queries), namely, queries that ask only for the
                 length of the shortest path; a state-of-the-art
                 technique was examined based on a faulty implementation
                 that led to incorrect query results. To address the
                 above issues, this paper presents a comprehensive
                 comparison of the most advanced spatial-coherence-based
                 and vertex-importance-based approaches. Using a variety
                 of real road networks with up to twenty million
                 vertices, we evaluated each technique in terms of its
                 preprocessing time, space consumption, and query
                 efficiency (for both shortest path and distance
                 queries). Our experimental results reveal the
                 characteristics of different techniques, based on which
                 we provide guidelines on selecting appropriate methods
                 for various scenarios.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Erdos:2012:FPP,
  author =       "D{\'o}ra Erd{\"o}s and Vatche Ishakian and Andrei
                 Lapets and Evimaria Terzi and Azer Bestavros",
  title =        "The filter-placement problem and its application to
                 minimizing information multiplicity",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "418--429",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In many information networks, data items --- such as
                 updates in social networks, news flowing through
                 interconnected RSS feeds and blogs, measurements in
                 sensor networks, route updates in ad-hoc networks ---
                 propagate in an uncoordinated manner: nodes often relay
                 information they receive to neighbors, independent of
                 whether or not these neighbors received the same
                 information from other sources. This uncoordinated data
                 dissemination may result in significant, yet
                 unnecessary communication and processing overheads,
                 ultimately reducing the utility of information
                 networks. To alleviate the negative impacts of this
                 information multiplicity phenomenon, we propose that a
                 subset of nodes (selected at key positions in the
                 network) carry out additional information filtering
                 functionality. Thus, nodes are responsible for the
                 removal (or significant reduction) of the redundant
                 data items relayed through them. We refer to such nodes
                 as filters. We formally define the Filter Placement
                 problem as a combinatorial optimization problem, and
                 study its computational complexity for different types
                 of graphs. We also present polynomial-time
                 approximation algorithms and scalable heuristics for
                 the problem. Our experimental results, which we
                 obtained through extensive simulations on synthetic and
                 real-world information flow networks, suggest that in
                 many settings a relatively small number of filters are
                 fairly effective in removing a large fraction of
                 redundant information.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Satuluri:2012:BLS,
  author =       "Venu Satuluri and Srinivasan Parthasarathy",
  title =        "{Bayesian} locality sensitive hashing for fast
                 similarity search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "430--441",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Given a collection of objects and an associated
                 similarity measure, the all-pairs similarity search
                 problem asks us to find all pairs of objects with
                 similarity greater than a certain user-specified
                 threshold. Locality-sensitive hashing (LSH) based
                 methods have become a very popular approach for this
                 problem. However, most such methods only use LSH for
                 the first phase of similarity search --- i.e. efficient
                 indexing for candidate generation. In this paper, we
                 present BayesLSH, a principled Bayesian algorithm for
                 the subsequent phase of similarity search ---
                 performing candidate pruning and similarity estimation
                 using LSH. A simpler variant, BayesLSH-Lite, which
                 calculates similarities exactly, is also presented. Our
                 algorithms are able to quickly prune away a large
                 majority of the false positive candidate pairs, leading
                 to significant speedups over baseline approaches. For
                 BayesLSH, we also provide probabilistic guarantees on
                 the quality of the output, both in terms of accuracy
                 and recall. Finally, the quality of BayesLSH's output
                 can be easily tuned and does not require any manual
                 setting of the number of hashes to use for similarity
                 estimation, unlike standard approaches. For two
                 state-of-the-art candidate generation algorithms,
                 AllPairs and LSH, BayesLSH enables significant
                 speedups, typically in the range 2x-20x for a wide
                 variety of datasets.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fujiwara:2012:FET,
  author =       "Yasuhiro Fujiwara and Makoto Nakatsuji and Makoto
                 Onizuka and Masaru Kitsuregawa",
  title =        "Fast and exact top-$k$ search for random walk with
                 restart",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "442--453",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Graphs are fundamental data structures and have been
                 employed for centuries to model real-world systems and
                 phenomena. Random walk with restart (RWR) provides a
                 good proximity score between two nodes in a graph, and
                 it has been successfully used in many applications such
                 as automatic image captioning, recommender systems, and
                 link prediction. The goal of this work is to find nodes
                 that have top-$k$ highest proximities for a given node.
                 Previous approaches to this problem find nodes
                 efficiently at the expense of exactness. The main
                 motivation of this paper is to answer, in the
                 affirmative, the question, 'Is it possible to improve
                 the search time without sacrificing the exactness?'.
                 Our solution, K-dash, is based on two ideas: (1) It
                 computes the proximity of a selected node efficiently
                 by sparse matrices, and (2) It skips unnecessary
                 proximity computations when searching for the top-$k$
                 nodes. Theoretical analyses show that K-dash guarantees
                 result exactness. We perform comprehensive experiments
                 to verify the efficiency of K-dash. The results show
                 that K-dash can find top-$k$ nodes significantly faster
                 than the previous approaches while it guarantees
                 exactness.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bahmani:2012:DSS,
  author =       "Bahman Bahmani and Ravi Kumar and Sergei
                 Vassilvitskii",
  title =        "Densest subgraph in streaming and {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "454--465",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The problem of finding locally dense components of a
                 graph is an important primitive in data analysis, with
                 wide-ranging applications from community mining to spam
                 detection and the discovery of biological network
                 modules. In this paper we present new algorithms for
                 finding the densest subgraph in the streaming model.
                 For any $\epsilon > 0$, our algorithms make $O(\log_{1
                 + \epsilon} n)$ passes over the input and find a
                 subgraph whose density is guaranteed to be within a
                 factor $2 (1 + \epsilon)$ of the optimum. Our
                 algorithms are also easily parallelizable and we
                 illustrate this by realizing them in the MapReduce
                 model. In addition we perform extensive experimental
                 evaluation on massive real-world graphs showing the
                 performance and scalability of our algorithms in
                 practice.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Silva:2012:MAS,
  author =       "Arlei Silva and Wagner {Meira, Jr.} and Mohammed J.
                 Zaki",
  title =        "Mining attribute-structure correlated patterns in
                 large attributed graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "466--477",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this work, we study the correlation between
                 attribute sets and the occurrence of dense subgraphs in
                 large attributed graphs, a task we call structural
                 correlation pattern mining. A structural correlation
                 pattern is a dense subgraph induced by a particular
                 attribute set. Existing methods are not able to extract
                 relevant knowledge regarding how vertex attributes
                 interact with dense subgraphs. Structural correlation
                 pattern mining combines aspects of frequent itemset and
                 quasi-clique mining problems. We propose statistical
                 significance measures that compare the structural
                 correlation of attribute sets against their expected
                 values using null models. Moreover, we evaluate the
                 interestingness of structural correlation patterns in
                 terms of size and density. An efficient algorithm that
                 combines search and pruning strategies in the
                 identification of the most relevant structural
                 correlation patterns is presented. We apply our method
                 for the analysis of three real-world attributed graphs:
                 a collaboration, a music, and a citation network,
                 verifying that it provides valuable knowledge in a
                 feasible time.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Schnaitter:2012:SAI,
  author =       "Karl Schnaitter and Neoklis Polyzotis",
  title =        "Semi-automatic index tuning: keeping {DBAs} in the
                 loop",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "478--489",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "To obtain a high level of system performance, a
                 database administrator (DBA) must choose a set of
                 indices that is appropriate for the workload. The
                 system can aid in this challenging task by providing
                 recommendations for the index configuration. We propose
                 a new index recommendation technique, termed
                 semi-automatic tuning, that keeps the DBA ``in the
                 loop'' by generating recommendations that use feedback
                 about the DBA's preferences. The technique also works
                 online, which avoids the limitations of commercial
                 tools that require the workload to be known in advance.
                 The foundation of our approach is the Work Function
                 Algorithm, which can solve a wide variety of online
                 optimization problems with strong competitive
                 guarantees. We present an experimental analysis that
                 validates the benefits of semi-automatic tuning in a
                 wide variety of conditions.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fink:2012:APD,
  author =       "Robert Fink and Larisa Han and Dan Olteanu",
  title =        "Aggregation in probabilistic databases via knowledge
                 compilation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "5",
  pages =        "490--501",
  month =        jan,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:13 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper presents a query evaluation technique for
                 positive relational algebra queries with aggregates on
                 a representation system for probabilistic data based on
                 the algebraic structures of semiring and semimodule.
                 The core of our evaluation technique is a procedure
                 that compiles semimodule and semiring expressions into
                 so-called decomposition trees, for which the
                 computation of the probability distribution can be done
                 in time linear in the product of the sizes of the
                 probability distributions represented by its nodes. We
                 give syntactic characterisations of tractable queries
                 with aggregates by exploiting the connection between
                 query tractability and polynomial-time decomposition
                 trees. A prototype of the technique is incorporated in
                 the probabilistic database engine SPROUT. We report on
                 performance experiments with custom datasets and TPC-H
                 data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Halim:2012:SDC,
  author =       "Felix Halim and Stratos Idreos and Panagiotis Karras
                 and Roland H. C. Yap",
  title =        "Stochastic database cracking: towards robust adaptive
                 indexing in main-memory column-stores",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "502--513",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Modern business applications and scientific databases
                 call for inherently dynamic data storage environments.
                 Such environments are characterized by two challenging
                 features: (a) they have little idle system time to
                 devote on physical design; and (b) there is little, if
                 any, a priori workload knowledge, while the query and
                 data workload keeps changing dynamically. In such
                 environments, traditional approaches to index building
                 and maintenance cannot apply. Database cracking has
                 been proposed as a solution that allows on-the-fly
                 physical data reorganization, as a collateral effect of
                 query processing. Cracking aims to continuously and
                 automatically adapt indexes to the workload at hand,
                 without human intervention. Indexes are built
                 incrementally, adaptively, and on demand. Nevertheless,
                 as we show, existing adaptive indexing methods fail to
                 deliver workload-robustness; they perform much better
                 with random workloads than with others. This frailty
                 derives from the inelasticity with which these
                 approaches interpret each query as a hint on how data
                 should be stored. Current cracking schemes blindly
                 reorganize the data within each query's range, even if
                 that results into successive expensive operations with
                 minimal indexing benefit. In this paper, we introduce
                 stochastic cracking, a significantly more resilient
                 approach to adaptive indexing. Stochastic cracking also
                 uses each query as a hint on how to reorganize data,
                 but not blindly so; it gains resilience and avoids
                 performance bottlenecks by deliberately applying
                 certain arbitrary choices in its decision-making.
                 Thereby, we bring adaptive indexing forward to a mature
                 formulation that confers the workload-robustness
                 previous approaches lacked. Our extensive experimental
                 study verifies that stochastic cracking maintains the
                 desired properties of original database cracking while
                 at the same time it performs well with diverse
                 realistic workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2012:AMA,
  author =       "Chao Li and Gerome Miklau",
  title =        "An adaptive mechanism for accurate query answering
                 under differential privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "514--525",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We propose a novel mechanism for answering sets of
                 counting queries under differential privacy. Given a
                 workload of counting queries, the mechanism
                 automatically selects a different set of ``strategy''
                 queries to answer privately, using those answers to
                 derive answers to the workload. The main algorithm
                 proposed in this paper approximates the optimal
                 strategy for any workload of linear counting queries.
                 With no cost to the privacy guarantee, the mechanism
                 improves significantly on prior approaches and achieves
                 near-optimal error for many workloads, when applied
                 under $(\epsilon, \delta)$-differential privacy. The
                 result is an adaptive mechanism which can help users
                 achieve good utility without requiring that they reason
                 carefully about the best formulation of their task.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Giannikis:2012:SKO,
  author =       "Georgios Giannikis and Gustavo Alonso and Donald
                 Kossmann",
  title =        "{SharedDB}: killing one thousand queries with one
                 stone",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "526--537",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Traditional database systems are built around the
                 query-at-a-time model. This approach tries to optimize
                 performance in a best-effort way. Unfortunately, best
                 effort is not good enough for many modern applications.
                 These applications require response time guarantees in
                 high load situations. This paper describes the design
                 of a new database architecture that is based on
                 batching queries and shared computation across possibly
                 hundreds of concurrent queries and updates. Performance
                 experiments with the TPC-W benchmark show that the
                 performance of our implementation, SharedDB, is indeed
                 robust across a wide range of dynamic workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Selke:2012:PBC,
  author =       "Joachim Selke and Christoph Lofi and Wolf-Tilo Balke",
  title =        "Pushing the boundaries of crowd-enabled databases with
                 query-driven schema expansion",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "538--549",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "By incorporating human workers into the query
                 execution process crowd-enabled databases facilitate
                 intelligent, social capabilities like completing
                 missing data at query time or performing cognitive
                 operators. But despite all their flexibility,
                 crowd-enabled databases still maintain rigid schemas.
                 In this paper, we extend crowd-enabled databases by
                 flexible query-driven schema expansion, allowing the
                 addition of new attributes to the database at query
                 time. However, the number of crowd-sourced mini-tasks
                 to fill in missing values may often be prohibitively
                 large and the resulting data quality is doubtful.
                 Instead of simple crowd-sourcing to obtain all values
                 individually, we leverage the usergenerated data found
                 in the Social Web: By exploiting user ratings we build
                 perceptual spaces, i.e., highly-compressed
                 representations of opinions, impressions, and
                 perceptions of large numbers of users. Using few
                 training samples obtained by expert crowd sourcing, we
                 then can extract all missing data automatically from
                 the perceptual space with high quality and at low
                 costs. Extensive experiments show that our approach can
                 boost both performance and quality of crowd-enabled
                 databases, while also providing the flexibility to
                 expand schemas in a query-driven fashion.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhao:2012:BAD,
  author =       "Bo Zhao and Benjamin I. P. Rubinstein and Jim Gemmell
                 and Jiawei Han",
  title =        "A {Bayesian} approach to discovering truth from
                 conflicting sources for data integration",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "550--561",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In practical data integration systems, it is common
                 for the data sources being integrated to provide
                 conflicting information about the same entity.
                 Consequently, a major challenge for data integration is
                 to derive the most complete and accurate integrated
                 records from diverse and sometimes conflicting sources.
                 We term this challenge the truth finding problem. We
                 observe that some sources are generally more reliable
                 than others, and therefore a good model of source
                 quality is the key to solving the truth finding
                 problem. In this work, we propose a probabilistic
                 graphical model that can automatically infer true
                 records and source quality without any supervision. In
                 contrast to previous methods, our principled approach
                 leverages a generative process of two types of errors
                 (false positive and false negative) by modeling two
                 different aspects of source quality. In so doing, ours
                 is also the first approach designed to merge
                 multi-valued attribute types. Our method is scalable,
                 due to an efficient sampling-based inference algorithm
                 that needs very few iterations in practice and enjoys
                 linear time complexity, with an even faster incremental
                 variant. Experiments on two real world datasets show
                 that our new method outperforms existing
                 state-of-the-art approaches to the truth finding
                 problem.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Upadhyaya:2012:HPS,
  author =       "Prasang Upadhyaya and Magdalena Balazinska and Dan
                 Suciu",
  title =        "How to price shared optimizations in the cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "562--573",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Data-management-as-a-service systems are increasingly
                 being used in collaborative settings, where multiple
                 users access common datasets. Cloud providers have the
                 choice to implement various optimizations, such as
                 indexing or materialized views, to accelerate queries
                 over these datasets. Each optimization carries a cost
                 and may benefit multiple users. This creates a major
                 challenge: how to select which optimizations to perform
                 and how to share their cost among users. The problem is
                 especially challenging when users are selfish and will
                 only report their true values for different
                 optimizations if doing so maximizes their utility. In
                 this paper, we present a new approach for selecting and
                 pricing shared optimizations by using Mechanism Design.
                 We first show how to apply the Shapley Value Mechanism
                 to the simple case of selecting and pricing additive
                 optimizations, assuming an offline game where all users
                 access the service for the same time-period. Second, we
                 extend the approach to online scenarios where users
                 come and go. Finally, we consider the case of
                 substitutive optimizations. We show analytically that
                 our mechanisms induce truthfulness and recover the
                 optimization costs. We also show experimentally that
                 our mechanisms yield higher utility than the
                 state-of-the-art approach based on regret
                 accumulation.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Angel:2012:DSM,
  author =       "Albert Angel and Nikos Sarkas and Nick Koudas and
                 Divesh Srivastava",
  title =        "Dense subgraph maintenance under streaming edge weight
                 updates for real-time story identification",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "574--585",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Recent years have witnessed an unprecedented
                 proliferation of social media. People around the globe
                 author, every day, millions of blog posts, micro-blog
                 posts, social network status updates, etc. This rich
                 stream of information can be used to identify, on an
                 ongoing basis, emerging stories, and events that
                 capture popular attention. Stories can be identified
                 via groups of tightly-coupled real-world entities,
                 namely the people, locations, products, etc., that are
                 involved in the story. The sheer scale, and rapid
                 evolution of the data involved necessitate highly
                 efficient techniques for identifying important stories
                 at every point of time. The main challenge in real-time
                 story identification is the maintenance of dense
                 subgraphs (corresponding to groups of tightly-coupled
                 entities) under streaming edge weight updates
                 (resulting from a stream of user-generated content).
                 This is the first work to study the efficient
                 maintenance of dense subgraphs under such streaming
                 edge weight updates. For a wide range of definitions of
                 density, we derive theoretical results regarding the
                 magnitude of change that a single edge weight update
                 can cause. Based on these, we propose a novel
                 algorithm, DynDens, which outperforms adaptations of
                 existing techniques to this setting, and yields
                 meaningful results. Our approach is validated by a
                 thorough experimental evaluation on large-scale real
                 and synthetic datasets.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Elghandour:2012:RRR,
  author =       "Iman Elghandour and Ashraf Aboulnaga",
  title =        "{ReStore}: reusing results of {MapReduce} jobs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "6",
  pages =        "586--597",
  month =        feb,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Sat Mar 24 07:52:15 MDT 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Analyzing large scale data has emerged as an important
                 activity for many organizations in the past few years.
                 This large scale data analysis is facilitated by the
                 MapReduce programming and execution model and its
                 implementations, most notably Hadoop. Users of
                 MapReduce often have analysis tasks that are too
                 complex to express as individual MapReduce jobs.
                 Instead, they use high-level query languages such as
                 Pig, Hive, or Jaql to express their complex tasks. The
                 compilers of these languages translate queries into
                 workflows of MapReduce jobs. Each job in these
                 workflows reads its input from the distributed file
                 system used by the MapReduce system and produces output
                 that is stored in this distributed file system and read
                 as input by the next job in the workflow. The current
                 practice is to delete these intermediate results from
                 the distributed file system at the end of executing the
                 workflow. One way to improve the performance of
                 workflows of MapReduce jobs is to keep these
                 intermediate results and reuse them for future
                 workflows submitted to the system. In this paper, we
                 present ReStore, a system that manages the storage and
                 reuse of such intermediate results. ReStore can reuse
                 the output of whole MapReduce jobs that are part of a
                 workflow, and it can also create additional reuse
                 opportunities by materializing and storing the output
                 of query execution operators that are executed within a
                 MapReduce job. We have implemented ReStore as an
                 extension to the Pig dataflow system on top of Hadoop,
                 and we experimentally demonstrate significant speedups
                 on queries from the PigMix benchmark.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Khoussainova:2012:PDM,
  author =       "Nodira Khoussainova and Magdalena Balazinska and Dan
                 Suciu",
  title =        "{PerfXplain}: debugging {MapReduce} job performance",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "598--609",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "While users today have access to many tools that
                 assist in performing large scale data analysis tasks,
                 understanding the performance characteristics of their
                 parallel computations, such as MapReduce jobs, remains
                 difficult. We present PerfXplain, a system that enables
                 users to ask questions about the relative performances
                 (i.e., runtimes) of pairs of MapReduce jobs. PerfXplain
                 provides a new query language for articulating
                 performance queries and an algorithm for generating
                 explanations from a log of past MapReduce job
                 executions. We formally define the notion of an
                 explanation together with three metrics, relevance,
                 precision, and generality, that measure explanation
                 quality. We present the explanation-generation
                 algorithm based on techniques related to decision-tree
                 building. We evaluate the approach on a log of past
                 executions on Amazon EC2, and show that our approach
                 can generate quality explanations, outperforming two
                 na{\"\i}ve explanation-generation methods.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gullo:2012:UCB,
  author =       "Francesco Gullo and Andrea Tagarelli",
  title =        "Uncertain centroid based partitional clustering of
                 uncertain data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "610--621",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Clustering uncertain data has emerged as a challenging
                 task in uncertain data management and mining. Thanks to
                 a computational complexity advantage over other
                 clustering paradigms, partitional clustering has been
                 particularly studied and a number of algorithms have
                 been developed. While existing proposals differ mainly
                 in the notions of cluster centroid and clustering
                 objective function, little attention has been given to
                 an analysis of their characteristics and limits. In
                 this work, we theoretically investigate major existing
                 methods of partitional clustering, and alternatively
                 propose a well-founded approach to clustering uncertain
                 data based on a novel notion of cluster centroid. A
                 cluster centroid is seen as an uncertain object defined
                 in terms of a random variable whose realizations are
                 derived based on all deterministic representations of
                 the objects to be clustered. As demonstrated
                 theoretically and experimentally, this allows for
                 better representing a cluster of uncertain objects,
                 thus supporting a consistently improved clustering
                 performance while maintaining comparable efficiency
                 with existing partitional clustering algorithms.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bahmani:2012:SM,
  author =       "Bahman Bahmani and Benjamin Moseley and Andrea Vattani
                 and Ravi Kumar and Sergei Vassilvitskii",
  title =        "Scalable $k$-means$++$",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "622--633",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Over half a century old and showing no signs of aging,
                 $k$-means remains one of the most popular data
                 processing algorithms. As is well-known, a proper
                 initialization of $k$-means is crucial for obtaining a
                 good final solution. The recently proposed $k$-means++
                 initialization algorithm achieves this, obtaining an
                 initial set of centers that is provably close to the
                 optimum solution. A major downside of the $k$-means++
                 is its inherent sequential nature, which limits its
                 applicability to massive data: one must make $k$ passes
                 over the data to find a good initial set of centers. In
                 this work we show how to drastically reduce the number
                 of passes needed to obtain, in parallel, a good
                 initialization. This is unlike prevailing efforts on
                 parallelizing $k$-means that have mostly focused on the
                 post-initialization phases of $k$-means. We prove that
                 our proposed initialization algorithm $k$-means||
                 obtains a nearly optimal solution after a logarithmic
                 number of passes, and then show that in practice a
                 constant number of passes suffices. Experimental
                 evaluation on real-world large-scale data demonstrates
                 that $k$-means|| outperforms $k$-means++ in both
                 sequential and parallel settings.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Benedikt:2012:QSA,
  author =       "Michael Benedikt and Pierre Bourhis and Clemens Ley",
  title =        "Querying schemas with access restrictions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "634--645",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We study verification of systems whose transitions
                 consist of accesses to a Web-based data-source. An
                 access is a lookup on a relation within a relational
                 database, fixing values for a set of positions in the
                 relation. For example, a transition can represent
                 access to a Web form, where the user is restricted to
                 filling in values for a particular set of fields. We
                 look at verifying properties of a schema describing the
                 possible accesses of such a system. We present a
                 language where one can describe the properties of an
                 access path, and also specify additional restrictions
                 on accesses that are enforced by the schema. Our main
                 property language, AccLTL, is based on a first-order
                 extension of linear-time temporal logic, interpreting
                 access paths as sequences of relational structures. We
                 also present a lower-level automaton model, A-automata,
                 which AccLTL specifications can compile into. We show
                 that AccLTL and A-automata can express static analysis
                 problems related to ``querying with limited access
                 patterns'' that have been studied in the database
                 literature in the past, such as whether an access is
                 relevant to answering a query, and whether two queries
                 are equivalent in the accessible data they can return.
                 We prove decidability and complexity results for
                 several restrictions and variants of AccLTL, and
                 explain which properties of paths can be expressed in
                 each restriction.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Graefe:2012:DDR,
  author =       "Goetz Graefe and Harumi Kuno",
  title =        "Definition, detection, and recovery of single-page
                 failures, a fourth class of database failures",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "646--655",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The three traditional failure classes are system,
                 media, and transaction failures. Sometimes, however,
                 modern storage exhibits failures that differ from all
                 of those. In order to capture and describe such cases,
                 single-page failures are introduced as a fourth failure
                 class. This class encompasses all failures to read a
                 data page correctly and with plausible contents despite
                 all correction attempts in lower system levels.
                 Efficient recovery seems to require a new data
                 structure called the page recovery index. Its
                 transactional maintenance can be accomplished writing
                 the same number of log records as today's efficient
                 implementations of logging and recovery. Detection and
                 recovery of a single-page failure can be sufficiently
                 fast that the affected data access is merely delayed,
                 without the need to abort the transaction.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Graefe:2012:CCA,
  author =       "Goetz Graefe and Felix Halim and Stratos Idreos and
                 Harumi Kuno and Stefan Manegold",
  title =        "Concurrency control for adaptive indexing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "656--667",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Adaptive indexing initializes and optimizes indexes
                 incrementally, as a side effect of query processing.
                 The goal is to achieve the benefits of indexes while
                 hiding or minimizing the costs of index creation.
                 However, index-optimizing side effects seem to turn
                 read-only queries into update transactions that might,
                 for example, create lock contention. This paper studies
                 concurrency control in the context of adaptive
                 indexing. We show that the design and implementation of
                 adaptive indexing rigorously separates index structures
                 from index contents; this relaxes the constraints and
                 requirements during adaptive indexing compared to those
                 of traditional index updates. Our design adapts to the
                 fact that an adaptive index is refined continuously,
                 and exploits any concurrency opportunities in a dynamic
                 way. A detailed experimental analysis demonstrates that
                 (a) adaptive indexing maintains its adaptive properties
                 even when running concurrent queries, (b) adaptive
                 indexing can exploit the opportunity for parallelism
                 due to concurrent queries, (c) the number of
                 concurrency conflicts and any concurrency
                 administration overheads follow an adaptive behavior,
                 decreasing as the workload evolves and adapting to the
                 workload needs.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zeng:2012:CSB,
  author =       "Qiang Zeng and Hai Zhuge",
  title =        "Comments on {``Stack-based Algorithms for Pattern
                 Matching on DAGs''}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "668--679",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The paper ``Stack-based Algorithms for Pattern
                 Matching on DAGs'' generalizes the classical holistic
                 twig join algorithms and proposes PathStackD,
                 TwigStackD and DagStackD to respectively evaluate path,
                 twig and DAG pattern queries on directed acyclic
                 graphs. In this paper, we investigate the major results
                 of that paper, pointing out several discrepancies and
                 proposing solutions to resolving them. We show that the
                 original algorithms do not find particular types of
                 query solutions that are common in practice. We also
                 analyze the effect of an underlying assumption on the
                 correctness of the algorithms and discuss the
                 pre-filtering process that the original work proposes
                 to prune redundant nodes. Our experimental study on
                 both real and synthetic data substantiates our
                 conclusions.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dalvi:2012:ASD,
  author =       "Nilesh Dalvi and Ashwin Machanavajjhala and Bo Pang",
  title =        "An analysis of structured data on the web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "7",
  pages =        "680--691",
  month =        mar,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:09 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this paper, we analyze the nature and distribution
                 of structured data on the Web. Web-scale information
                 extraction, or the problem of creating structured
                 tables using extraction from the entire web, is
                 gathering lots of research interest. We perform a study
                 to understand and quantify the value of Web-scale
                 extraction, and how structured information is
                 distributed amongst top aggregator websites and tail
                 sites for various interesting domains. We believe this
                 is the first study of its kind, and gives us new
                 insights for information extraction over the Web.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mouratidis:2012:SPC,
  author =       "Kyriakos Mouratidis and Man Lung Yiu",
  title =        "Shortest path computation with no information
                 leakage",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "692--703",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Shortest path computation is one of the most common
                 queries in location-based services (LBSs). Although
                 particularly useful, such queries raise serious privacy
                 concerns. Exposing to a (potentially untrusted) LBS the
                 client's position and her destination may reveal
                 personal information, such as social habits, health
                 condition, shopping preferences, lifestyle choices,
                 etc. The only existing method for privacy-preserving
                 shortest path computation follows the obfuscation
                 paradigm; it prevents the LBS from inferring the source
                 and destination of the query with a probability higher
                 than a threshold. This implies, however, that the LBS
                 still deduces some information (albeit not exact) about
                 the client's location and her destination. In this
                 paper we aim at strong privacy, where the adversary
                 learns nothing about the shortest path query. We
                 achieve this via established private information
                 retrieval techniques, which we treat as black-box
                 building blocks. Experiments on real, large-scale road
                 networks assess the practicality of our schemes.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Metwally:2012:VSJ,
  author =       "Ahmed Metwally and Christos Faloutsos",
  title =        "{V-SMART-join}: a scalable {MapReduce} framework for
                 all-pair similarity joins of multisets and vectors",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "704--715",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This work proposes V-SMART-Join, a scalable
                 MapReduce-based framework for discovering all pairs of
                 similar entities. The V-SMART-Join framework is
                 applicable to sets, multisets, and vectors.
                 V-SMART-Join is motivated by the observed skew in the
                 underlying distributions of Internet traffic, and is a
                 family of 2-stage algorithms, where the first stage
                 computes and joins the partial results, and the second
                 stage computes the similarity exactly for all candidate
                 pairs. The V-SMART-Join algorithms are very efficient
                 and scalable in the number of entities, as well as
                 their cardinalities. They were up to 30 times faster
                 than the state of the art algorithm, VCL, when compared
                 on a real dataset of a small size. We also established
                 the scalability of the proposed algorithms by running
                 them on a dataset of a realistic size, on which VCL
                 never succeeded to finish. Experiments were run using
                 real datasets of IPs and cookies, where each IP is
                 represented as a multiset of cookies, and the goal is
                 to discover similar IPs to identify Internet proxies.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Low:2012:DGF,
  author =       "Yucheng Low and Danny Bickson and Joseph Gonzalez and
                 Carlos Guestrin and Aapo Kyrola and Joseph M.
                 Hellerstein",
  title =        "{Distributed GraphLab}: a framework for machine
                 learning and data mining in the cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "716--727",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "While high-level data parallel frameworks, like
                 MapReduce, simplify the design and implementation of
                 large-scale data processing systems, they do not
                 naturally or efficiently support many important data
                 mining and machine learning algorithms and can lead to
                 inefficient learning systems. To help fill this
                 critical void, we introduced the GraphLab abstraction
                 which naturally expresses asynchronous, dynamic,
                 graph-parallel computation while ensuring data
                 consistency and achieving a high degree of parallel
                 performance in the shared-memory setting. In this
                 paper, we extend the GraphLab framework to the
                 substantially more challenging distributed setting
                 while preserving strong data consistency guarantees. We
                 develop graph based extensions to pipelined locking and
                 data versioning to reduce network congestion and
                 mitigate the effect of network latency. We also
                 introduce fault tolerance to the GraphLab abstraction
                 using the classic Chandy-Lamport snapshot algorithm and
                 demonstrate how it can be easily implemented by
                 exploiting the GraphLab abstraction itself. Finally, we
                 evaluate our distributed implementation of the GraphLab
                 abstraction on a large Amazon EC2 deployment and show
                 1-2 orders of magnitude performance gains over
                 Hadoop-based implementations.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zeng:2012:ALO,
  author =       "Qiang Zeng and Xiaorui Jiang and Hai Zhuge",
  title =        "Adding logical operators to tree pattern queries on
                 graph-structured data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "728--739",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As data are increasingly modeled as graphs for
                 expressing complex relationships, the tree pattern
                 query on graph-structured data becomes an important
                 type of queries in real-world applications. Most
                 practical query languages, such as XQuery and SPARQL,
                 support logical expressions using logical-AND/OR/NOT
                 operators to define structural constraints of tree
                 patterns. In this paper, (1) we propose generalized
                 tree pattern queries (GTPQs) over graph-structured
                 data, which fully support propositional logic of
                 structural constraints. (2) We make a thorough study of
                 fundamental problems including satisfiability,
                 containment and minimization, and analyze the
                 computational complexity and the decision procedures of
                 these problems. (3) We propose a compact graph
                 representation of intermediate results and a pruning
                 approach to reduce the size of intermediate results and
                 the number of join operations --- two factors that
                 often impair the efficiency of traditional algorithms
                 for evaluating tree pattern queries. (4) We present an
                 efficient algorithm for evaluating GTPQs using 3-hop as
                 the underlying reachability index. (5) Experiments on
                 both real-life and synthetic data sets demonstrate the
                 effectiveness and efficiency of our algorithm, from
                 several times to orders of magnitude faster than
                 state-of-the-art algorithms in terms of evaluation
                 time, even for traditional tree pattern queries with
                 only conjunctive operations.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Singh:2012:LSS,
  author =       "Rishabh Singh and Sumit Gulwani",
  title =        "Learning semantic string transformations from
                 examples",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "740--751",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We address the problem of performing semantic
                 transformations on strings, which may represent a
                 variety of data types (or their combination) such as a
                 column in a relational table, time, date, currency,
                 etc. Unlike syntactic transformations, which are based
                 on regular expressions and which interpret a string as
                 a sequence of characters, semantic transformations
                 additionally require exploiting the semantics of the
                 data type represented by the string, which may be
                 encoded as a database of relational tables. Manually
                 performing such transformations on a large collection
                 of strings is error prone and cumbersome, while
                 programmatic solutions are beyond the skill-set of
                 end-users. We present a programming by example
                 technology that allows end-users to automate such
                 repetitive tasks. We describe an expressive
                 transformation language for semantic manipulation that
                 combines table lookup operations and syntactic
                 manipulations. We then present a synthesis algorithm
                 that can learn all transformations in the language that
                 are consistent with the user-provided set of
                 input-output examples. We have implemented this
                 technology as an add-in for the Microsoft Excel
                 Spreadsheet system and have evaluated it successfully
                 over several benchmarks picked from various Excel
                 help-forums.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2012:CDD,
  author =       "Changbin Liu and Lu Ren and Boon Thau Loo and Yun Mao
                 and Prithwish Basu",
  title =        "{Cologne}: a declarative distributed constraint
                 optimization platform",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "752--763",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper presents Cologne, a declarative
                 optimization platform that enables constraint
                 optimization problems (COPs) to be declaratively
                 specified and incrementally executed in distributed
                 systems. Cologne integrates a declarative networking
                 engine with an off-the-shelf constraint solver. We have
                 developed the Colog language that combines distributed
                 Datalog used in declarative networking with language
                 constructs for specifying goals and constraints used in
                 COPs. Cologne uses novel query processing strategies
                 for processing Colog programs, by combining the use of
                 bottom-up distributed Datalog evaluation with top-down
                 goal-oriented constraint solving. Using case studies
                 based on cloud and wireless network optimizations, we
                 demonstrate that Cologne (1) can flexibly support a
                 wide range of policy-based optimizations in distributed
                 systems, (2) results in orders of magnitude less code
                 compared to imperative implementations, and (3) is
                 highly efficient with low overhead and fast convergence
                 times.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2012:OBA,
  author =       "Yi Zhang and Jun Yang",
  title =        "Optimizing {I/O} for big array analytics",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "764--775",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Big array analytics is becoming indispensable in
                 answering important scientific and business questions.
                 Most analysis tasks consist of multiple steps, each
                 making one or multiple passes over the arrays to be
                 analyzed and generating intermediate results. In the
                 big data setting, I/O optimization is a key to
                 efficient analytics. In this paper, we develop a
                 framework and techniques for capturing a broad range of
                 analysis tasks expressible in nested-loop forms,
                 representing them in a declarative way, and optimizing
                 their I/O by identifying sharing opportunities.
                 Experiment results show that our optimizer is capable
                 of finding execution plans that exploit nontrivial I/O
                 sharing opportunities with significant savings.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bailis:2012:PBS,
  author =       "Peter Bailis and Shivaram Venkataraman and Michael J.
                 Franklin and Joseph M. Hellerstein and Ion Stoica",
  title =        "Probabilistically bounded staleness for practical
                 partial quorums",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "8",
  pages =        "776--787",
  month =        apr,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:10 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Data store replication results in a fundamental
                 trade-off between operation latency and data
                 consistency. In this paper, we examine this trade-off
                 in the context of quorum-replicated data stores. Under
                 partial, or non-strict quorum replication, a data store
                 waits for responses from a subset of replicas before
                 answering a query, without guaranteeing that read and
                 write replica sets intersect. As deployed in practice,
                 these configurations provide only basic eventual
                 consistency guarantees, with no limit to the recency of
                 data returned. However, anecdotally, partial quorums
                 are often ``good enough'' for practitioners given their
                 latency benefits. In this work, we explain why partial
                 quorums are regularly acceptable in practice, analyzing
                 both the staleness of data they return and the latency
                 benefits they offer. We introduce Probabilistically
                 Bounded Staleness (PBS) consistency, which provides
                 expected bounds on staleness with respect to both
                 versions and wall clock time. We derive a closed-form
                 solution for versioned staleness as well as model
                 real-time staleness for representative Dynamo-style
                 systems under internet-scale production workloads.
                 Using PBS, we measure the latency-consistency trade-off
                 for partial quorum systems. We quantitatively
                 demonstrate how eventually consistent systems
                 frequently return consistent data within tens of
                 milliseconds while offering significant latency
                 benefits.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sun:2012:ESM,
  author =       "Zhao Sun and Hongzhi Wang and Haixun Wang and Bin Shao
                 and Jianzhong Li",
  title =        "Efficient subgraph matching on billion node graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "788--799",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The ability to handle large scale graph data is
                 crucial to an increasing number of applications. Much
                 work has been dedicated to supporting basic graph
                 operations such as subgraph matching, reachability,
                 regular expression matching, etc. In many cases, graph
                 indices are employed to speed up query processing.
                 Typically, most indices require either super-linear
                 indexing time or super-linear indexing space.
                 Unfortunately, for very large graphs, super-linear
                 approaches are almost always infeasible. In this paper,
                 we study the problem of subgraph matching on
                 billion-node graphs. We present a novel algorithm that
                 supports efficient subgraph matching for graphs
                 deployed on a distributed memory store. Instead of
                 relying on super-linear indices, we use efficient graph
                 exploration and massive parallel computing for query
                 processing. Our experimental results demonstrate the
                 feasibility of performing subgraph matching on
                 web-scale graph data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yuan:2012:ESS,
  author =       "Ye Yuan and Guoren Wang and Lei Chen and Haixun Wang",
  title =        "Efficient subgraph similarity search on large
                 probabilistic graph databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "800--811",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Many studies have been conducted on seeking the
                 efficient solution for subgraph similarity search over
                 certain (deterministic) graphs due to its wide
                 application in many fields, including bioinformatics,
                 social network analysis, and Resource Description
                 Framework (RDF) data management. All these works assume
                 that the underlying data are certain. However, in
                 reality, graphs are often noisy and uncertain due to
                 various factors, such as errors in data extraction,
                 inconsistencies in data integration, and privacy
                 preserving purposes. Therefore, in this paper, we study
                 subgraph similarity search on large probabilistic graph
                 databases. Different from previous works assuming that
                 edges in an uncertain graph are independent of each
                 other, we study the uncertain graphs where edges'
                 occurrences are correlated. We formally prove that
                 subgraph similarity search over probabilistic graphs is
                 \#P-complete, thus, we employ a filter-and-verify
                 framework to speed up the search. In the filtering
                 phase, we develop tight lower and upper bounds of
                 subgraph similarity probability based on a
                 probabilistic matrix index, PMI. PMI is composed of
                 discriminative subgraph features associated with tight
                 lower and upper bounds of subgraph isomorphism
                 probability. Based on PMI, we can sort out a large
                 number of probabilistic graphs and maximize the pruning
                 capability. During the verification phase, we develop
                 an efficient sampling algorithm to validate the
                 remaining candidates. The efficiency of our proposed
                 solutions has been verified through extensive
                 experiments.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2012:TDM,
  author =       "Jia Wang and James Cheng",
  title =        "Truss decomposition in massive networks",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "812--823",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The $k$-truss is a type of cohesive subgraphs proposed
                 recently for the study of networks. While the problem
                 of computing most cohesive subgraphs is NP-hard, there
                 exists a polynomial time algorithm for computing
                 $k$-truss. Compared with $k$-core which is also
                 efficient to compute, $k$-truss represents the ``core''
                 of a $k$-core that keeps the key information of, while
                 filtering out less important information from, the
                 $k$-core. However, existing algorithms for computing
                 $k$-truss are inefficient for handling today's massive
                 networks. We first improve the existing in-memory
                 algorithm for computing $k$-truss in networks of
                 moderate size. Then, we propose two I/O-efficient
                 algorithms to handle massive networks that cannot fit
                 in main memory. Our experiments on real datasets verify
                 the efficiency of our algorithms and the value of
                 $k$-truss.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2012:SST,
  author =       "Ju Fan and Guoliang Li and Lizhu Zhou and Shanshan
                 Chen and Jun Hu",
  title =        "{Seal}: spatio-textual similarity search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "824--835",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Location-based services (LBS) have become more and
                 more ubiquitous recently. Existing methods focus on
                 finding relevant points-of-interest (POIs) based on
                 users' locations and query keywords. Nowadays, modern
                 LBS applications generate a new kind of spatio-textual
                 data, regions-of-interest (ROIs), containing
                 region-based spatial information and textual
                 description, e.g., mobile user profiles with active
                 regions and interest tags. To satisfy search
                 requirements on ROIs, we study a new research problem,
                 called spatio-textual similarity search: Given a set of
                 ROIs and a query ROI, we find the similar ROIs by
                 considering spatial overlap and textual similarity.
                 Spatio-textual similarity search has many important
                 applications, e.g., social marketing in location-aware
                 social networks. It calls for an efficient search
                 method to support large scales of spatio-textual data
                 in LBS systems. To this end, we introduce a
                 filter-and-verification framework to compute the
                 answers. In the filter step, we generate signatures for
                 the ROIs and the query, and utilize the signatures to
                 generate candidates whose signatures are similar to
                 that of the query. In the verification step, we verify
                 the candidates and identify the final answers. To
                 achieve high performance, we generate effective
                 high-quality signatures, and devise efficient filtering
                 algorithms as well as pruning techniques. Experimental
                 results on real and synthetic datasets show that our
                 method achieves high performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lappas:2012:SBT,
  author =       "Theodoros Lappas and Marcos R. Vieira and Dimitrios
                 Gunopulos and Vassilis J. Tsotras",
  title =        "On the spatiotemporal burstiness of terms",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "836--847",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Thousands of documents are made available to the users
                 via the web on a daily basis. One of the most
                 extensively studied problems in the context of such
                 document streams is burst identification. Given a term
                 t, a burst is generally exhibited when an unusually
                 high frequency is observed for t. While spatial and
                 temporal burstiness have been studied individually in
                 the past, our work is the first to simultaneously track
                 and measure spatiotemporal term burstiness. In
                 addition, we use the mined burstiness information
                 toward an efficient document-search engine: given a
                 user's query of terms, our engine returns a ranked list
                 of documents discussing influential events with a
                 strong spatiotemporal impact. We demonstrate the
                 efficiency of our methods with an extensive
                 experimental evaluation on real and synthetic
                 datasets.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shirani-Mehr:2012:ERQ,
  author =       "Houtan Shirani-Mehr and Farnoush Banaei-Kashani and
                 Cyrus Shahabi",
  title =        "Efficient reachability query evaluation in large
                 spatiotemporal contact datasets",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "848--859",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "With the advent of reliable positioning technologies
                 and prevalence of location-based services, it is now
                 feasible to accurately study the propagation of items
                 such as infectious viruses, sensitive information
                 pieces, and malwares through a population of moving
                 objects, e.g., individuals, mobile devices, and
                 vehicles. In such application scenarios, an item passes
                 between two objects when the objects are sufficiently
                 close (i.e., when they are, so-called, in contact), and
                 hence once an item is initiated, it can penetrate the
                 object population through the evolving network of
                 contacts among objects, termed contact network. In this
                 paper, for the first time we define and study
                 reachability queries in large (i.e., disk-resident)
                 contact datasets which record the movement of a
                 (potentially large) set of objects moving in a spatial
                 environment over an extended time period. A
                 reachability query verifies whether two objects are
                 ``reachable'' through the evolving contact network
                 represented by such contact datasets. We propose two
                 contact-dataset indexes that enable efficient
                 evaluation of such queries despite the potentially
                 humongous size of the contact datasets. With the first
                 index, termed ReachGrid, at the query time only a small
                 necessary portion of the contact network which is
                 required for reachability evaluation is constructed and
                 traversed. With the second approach, termed ReachGraph,
                 we precompute reachability at different scales and
                 leverage these precalculations at the query time for
                 efficient query processing. We optimize the placement
                 of both indexes on disk to enable efficient index
                 traversal during query processing. We study the pros
                 and cons of our proposed approaches by performing
                 extensive experiments with both real and synthetic
                 data. Based on our experimental results, our proposed
                 approaches outperform existing reachability query
                 processing techniques in contact networks by 76\% on
                 average.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Nguyen:2012:BMO,
  author =       "Thi Nguyen and Zhen He and Rui Zhang and Phillip
                 Ward",
  title =        "Boosting moving object indexing through velocity
                 partitioning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "860--871",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "There have been intense research interests in moving
                 object indexing in the past decade. However, existing
                 work did not exploit the important property of skewed
                 velocity distributions. In many real world scenarios,
                 objects travel predominantly along only a few
                 directions. Examples include vehicles on road networks,
                 flights, people walking on the streets, etc. The search
                 space for a query is heavily dependent on the velocity
                 distribution of the objects grouped in the nodes of an
                 index tree. Motivated by this observation, we propose
                 the velocity partitioning (VP) technique, which
                 exploits the skew in velocity distribution to speed up
                 query processing using moving object indexes. The VP
                 technique first identifies the ``dominant velocity axes
                 (DVAs)'' using a combination of principal components
                 analysis (PCA) and $k$-means clustering. Then, a moving
                 object index (e.g., a TPR-tree) is created based on
                 each DVA, using the DVA as an axis of the underlying
                 coordinate system. An object is maintained in the index
                 whose DVA is closest to the object's current moving
                 direction. Thus, all the objects in an index are moving
                 in a near 1-dimensional space instead of a
                 2-dimensional space. As a result, the expansion of the
                 search space with time is greatly reduced, from a
                 quadratic function of the maximum speed (of the objects
                 in the search range) to a near linear function of the
                 maximum speed. The VP technique can be applied to a
                 wide range of moving object index structures. We have
                 implemented the VP technique on two representative
                 ones, the TPR*-tree and the B$^x$-tree. Extensive
                 experiments validate that the VP technique consistently
                 improves the performance of those index structures.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bidoit-Tollu:2012:TBD,
  author =       "Nicole Bidoit-Tollu and Dario Colazzo and Federico
                 Ulliana",
  title =        "Type-based detection of {XML} query-update
                 independence",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "872--883",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper presents a novel static analysis technique
                 to detect XML query-update independence, in the
                 presence of a schema. Rather than types, our system
                 infers chains of types. Each chain represents a path
                 that can be traversed on a valid document during
                 query/update evaluation. The resulting independence
                 analysis is precise, although it raises a challenging
                 issue: recursive schemas may lead to inference of
                 infinitely many chains. A sound and complete
                 approximation technique ensuring a finite analysis in
                 any case is presented, together with an efficient
                 implementation performing the chain-based analysis in
                 polynomial space and time.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sowell:2012:MSD,
  author =       "Benjamin Sowell and Wojciech Golab and Mehul A. Shah",
  title =        "{Minuet}: a scalable distributed multiversion
                 {B}-tree",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "884--895",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Data management systems have traditionally been
                 designed to support either long-running analytics
                 queries or short-lived transactions, but an increasing
                 number of applications need both. For example, online
                 games, socio-mobile apps, and e-commerce sites need to
                 not only maintain operational state, but also analyze
                 that data quickly to make predictions and
                 recommendations that improve user experience. In this
                 paper, we present Minuet, a distributed, main-memory
                 B-tree that supports both transactions and
                 copy-on-write snapshots for in-situ analytics. Minuet
                 uses main-memory storage to enable low-latency
                 transactional operations as well as analytics queries
                 without compromising transaction performance. In
                 addition to supporting read-only analytics queries on
                 snapshots, Minuet supports writable clones, so that
                 users can create branching versions of the data. This
                 feature can be quite useful, e.g. to support complex
                 ``what-if'' analysis or to facilitate wide-area
                 replication. Our experiments show that Minuet
                 outperforms a commercial main-memory database in many
                 ways. It scales to hundreds of cores and TBs of memory,
                 and can process hundreds of thousands of B-tree
                 operations per second while executing long-running
                 scans.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yin:2012:CLT,
  author =       "Hongzhi Yin and Bin Cui and Jing Li and Junjie Yao and
                 Chen Chen",
  title =        "Challenging the long tail recommendation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "9",
  pages =        "896--907",
  month =        may,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:11 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The success of ``infinite-inventory'' retailers such
                 as Amazon.com and Netflix has been largely attributed
                 to a ``long tail'' phenomenon. Although the majority of
                 their inventory is not in high demand, these niche
                 products, unavailable at limited-inventory competitors,
                 generate a significant fraction of total revenue in
                 aggregate. In addition, tail product availability can
                 boost head sales by offering consumers the convenience
                 of ``one-stop shopping'' for both their mainstream and
                 niche tastes. However, most of existing recommender
                 systems, especially collaborative filter based methods,
                 can not recommend tail products due to the data
                 sparsity issue. It has been widely acknowledged that to
                 recommend popular products is easier yet more trivial
                 while to recommend long tail products adds more novelty
                 yet it is also a more challenging task. In this paper,
                 we propose a novel suite of graph-based algorithms for
                 the long tail recommendation. We first represent
                 user-item information with undirected edge-weighted
                 graph and investigate the theoretical foundation of
                 applying Hitting Time algorithm for long tail item
                 recommendation. To improve recommendation diversity and
                 accuracy, we extend Hitting Time and propose efficient
                 Absorbing Time algorithm to help users find their
                 favorite long tail items. Finally, we refine the
                 Absorbing Time algorithm and propose two entropy-biased
                 Absorbing Cost algorithms to distinguish the variation
                 on different user-item rating pairs, which further
                 enhances the effectiveness of long tail recommendation.
                 Empirical experiments on two real life datasets show
                 that our proposed algorithms are effective to recommend
                 long tail items and outperform state-of-the-art
                 recommendation techniques.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Pimplikar:2012:ATQ,
  author =       "Rakesh Pimplikar and Sunita Sarawagi",
  title =        "Answering table queries on the {Web} using column
                 keywords",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "908--919",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We present the design of a structured search engine
                 which returns a multi-column table in response to a
                 query consisting of keywords describing each of its
                 columns. We answer such queries by exploiting the
                 millions of tables on the Web because these are much
                 richer sources of structured knowledge than free-format
                 text. However, a corpus of tables harvested from
                 arbitrary HTML web pages presents huge challenges of
                 diversity and redundancy not seen in centrally edited
                 knowledge bases. We concentrate on one concrete task in
                 this paper. Given a set of Web tables T$_1$,\ldots{},
                 T$_n$, and a query Q with q sets of keywords
                 Q$_1$,\ldots{}, Q$_q$, decide for each T$_i$ if it is
                 relevant to Q and if so, identify the mapping between
                 the columns of T$_i$ and query columns. We represent
                 this task as a graphical model that jointly maps all
                 tables by incorporating diverse sources of clues
                 spanning matches in different parts of the table,
                 corpus-wide co-occurrence statistics, and content
                 overlap across table columns. We define a novel query
                 segmentation model for matching keywords to table
                 columns, and a robust mechanism of exploiting content
                 overlap across table columns. We design efficient
                 inference algorithms based on bipartite matching and
                 constrained graph cuts to solve the joint labeling
                 task. Experiments on a workload of 59 queries over a 25
                 million web table corpus shows significant boost in
                 accuracy over baseline IR methods.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Goodrich:2012:EVW,
  author =       "Michael T. Goodrich and Charalampos Papamanthou and
                 Duy Nguyen and Roberto Tamassia and Cristina Videira
                 Lopes and Olga Ohrimenko and Nikos Triandopoulos",
  title =        "Efficient verification of web-content searching
                 through authenticated web crawlers",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "920--931",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We consider the problem of verifying the correctness
                 and completeness of the result of a keyword search. We
                 introduce the concept of an authenticated web crawler
                 and present its design and prototype implementation. An
                 authenticated web crawler is a trusted program that
                 computes a specially-crafted signature over the web
                 contents it visits. This signature enables (i) the
                 verification of common Internet queries on web pages,
                 such as conjunctive keyword searches---this guarantees
                 that the output of a conjunctive keyword search is
                 correct and complete; (ii) the verification of the
                 content returned by such Internet queries---this
                 guarantees that web data is authentic and has not been
                 maliciously altered since the computation of the
                 signature by the crawler. In our solution, the search
                 engine returns a cryptographic proof of the query
                 result. Both the proof size and the verification time
                 are proportional only to the sizes of the query
                 description and the query result, but do not depend on
                 the number or sizes of the web pages over which the
                 search is performed. As we experimentally demonstrate,
                 the prototype implementation of our system provides a
                 low communication overhead between the search engine
                 and the user, and fast verification of the returned
                 results by the user.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Blunschi:2012:SGS,
  author =       "Lukas Blunschi and Claudio Jossen and Donald Kossmann
                 and Magdalini Mori and Kurt Stockinger",
  title =        "{SODA}: generating {SQL} for business users",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "932--943",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The purpose of data warehouses is to enable business
                 analysts to make better decisions. Over the years the
                 technology has matured and data warehouses have become
                 extremely successful. As a consequence, more and more
                 data has been added to the data warehouses and their
                 schemas have become increasingly complex. These systems
                 still work great in order to generate pre-canned
                 reports. However, with their current complexity, they
                 tend to be a poor match for non tech-savvy business
                 analysts who need answers to ad-hoc queries that were
                 not anticipated. This paper describes the design,
                 implementation, and experience of the SODA system
                 (Search over DAta Warehouse). SODA bridges the gap
                 between the business needs of analysts and the
                 technical complexity of current data warehouses. SODA
                 enables a Google-like search experience for data
                 warehouses by taking keyword queries of business users
                 and automatically generating executable SQL. The key
                 idea is to use a graph pattern matching algorithm that
                 uses the metadata model of the data warehouse. Our
                 results with real data from a global player in the
                 financial services industry show that SODA produces
                 queries with high precision and recall, and makes it
                 much easier for business users to interactively explore
                 highly-complex data warehouses.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Terrovitis:2012:PPD,
  author =       "Manolis Terrovitis and Nikos Mamoulis and John
                 Liagouris and Spiros Skiadopoulos",
  title =        "Privacy preservation by disassociation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "944--955",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this work, we focus on protection against identity
                 disclosure in the publication of sparse
                 multidimensional data. Existing multidimensional
                 anonymization techniques (a) protect the privacy of
                 users either by altering the set of quasi-identifiers
                 of the original data (e.g., by generalization or
                 suppression) or by adding noise (e.g., using
                 differential privacy) and/or (b) assume a clear
                 distinction between sensitive and non-sensitive
                 information and sever the possible linkage. In many
                 real world applications the above techniques are not
                 applicable. For instance, consider web search query
                 logs. Suppressing or generalizing anonymization methods
                 would remove the most valuable information in the
                 dataset: the original query terms. Additionally, web
                 search query logs contain millions of query terms which
                 cannot be categorized as sensitive or non-sensitive
                 since a term may be sensitive for a user and
                 non-sensitive for another. Motivated by this
                 observation, we propose an anonymization technique
                 termed disassociation that preserves the original terms
                 but hides the fact that two or more different terms
                 appear in the same record. We protect the users'
                 privacy by disassociating record terms that participate
                 in identifying combinations. This way the adversary
                 cannot associate with high probability a record with a
                 rare combination of terms. To the best of our
                 knowledge, our proposal is the first to employ such a
                 technique to provide protection against identity
                 disclosure. We propose an anonymization algorithm based
                 on our approach and evaluate its performance on real
                 and synthetic datasets, comparing it against other
                 state-of-the-art methods based on generalization and
                 differential privacy.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kanagal:2012:SRS,
  author =       "Bhargav Kanagal and Amr Ahmed and Sandeep Pandey and
                 Vanja Josifovski and Jeff Yuan and Lluis Garcia-Pueyo",
  title =        "Supercharging recommender systems using taxonomies for
                 learning user purchase behavior",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "956--967",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Recommender systems based on latent factor models have
                 been effectively used for understanding user interests
                 and predicting future actions. Such models work by
                 projecting the users and items into a smaller
                 dimensional space, thereby clustering similar users and
                 items together and subsequently compute similarity
                 between unknown user-item pairs. When user-item
                 interactions are sparse (sparsity problem) or when new
                 items continuously appear (cold start problem), these
                 models perform poorly. In this paper, we exploit the
                 combination of taxonomies and latent factor models to
                 mitigate these issues and improve recommendation
                 accuracy. We observe that taxonomies provide structure
                 similar to that of a latent factor model: namely, it
                 imposes human-labeled categories (clusters) over items.
                 This leads to our proposed taxonomy-aware latent factor
                 model (TF) which combines taxonomies and latent factors
                 using additive models. We develop efficient algorithms
                 to train the TF models, which scales to large number of
                 users/items and develop scalable
                 inference/recommendation algorithms by exploiting the
                 structure of the taxonomy. In addition, we extend the
                 TF model to account for the temporal dynamics of user
                 interests using high-order Markov chains. To deal with
                 large-scale data, we develop a parallel multi-core
                 implementation of our TF model. We empirically evaluate
                 the TF model for the task of predicting user purchases
                 using a real-world shopping dataset spanning more than
                 a million users and products. Our experiments
                 demonstrate the benefits of using our TF models over
                 existing approaches, in terms of both prediction
                 accuracy and running time.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ahmad:2012:DHO,
  author =       "Yanif Ahmad and Oliver Kennedy and Christoph Koch and
                 Milos Nikolic",
  title =        "{DBToaster}: higher-order delta processing for
                 dynamic, frequently fresh views",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "968--979",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Applications ranging from algorithmic trading to
                 scientific data analysis require realtime analytics
                 based on views over databases that change at very high
                 rates. Such views have to be kept fresh at low
                 maintenance cost and latencies. At the same time, these
                 views have to support classical SQL, rather than window
                 semantics, to enable applications that combine current
                 with aged or historical data. In this paper, we present
                 viewlet transforms, a recursive finite differencing
                 technique applied to queries. The viewlet transform
                 materializes a query and a set of its higher-order
                 deltas as views. These views support each other's
                 incremental maintenance, leading to a reduced overall
                 view maintenance cost. The viewlet transform of a query
                 admits efficient evaluation, the elimination of certain
                 expensive query operations, and aggressive
                 parallelization. We develop viewlet transforms into a
                 workable query execution technique, present a heuristic
                 and cost-based optimization framework, and report on
                 experiments with a prototype dynamic data management
                 system that combines viewlet transforms with an
                 optimizing compilation technique. The system supports
                 tens of thousands of complete view refreshes a second
                 for a wide range of queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agarwal:2012:RTD,
  author =       "Manoj K. Agarwal and Krithi Ramamritham and Manish
                 Bhide",
  title =        "Real time discovery of dense clusters in highly
                 dynamic graphs: identifying real world events in highly
                 dynamic environments",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "980--991",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Due to their real time nature, microblog streams are a
                 rich source of dynamic information, for example, about
                 emerging events. Existing techniques for discovering
                 such events from a microblog stream in real time (such
                 as Twitter trending topics), have several lacunae when
                 used for discovering emerging events; extant graph
                 based event detection techniques are not practical in
                 microblog settings due to their complexity; and
                 conventional techniques, which have been developed for
                 blogs, web-pages, etc., involving the use of keyword
                 search, are only useful for finding information about
                 known events. Hence, in this paper, we present
                 techniques to discover events that are unraveling in
                 microblog message streams in real time so that such
                 events can be reported as soon as they occur. We model
                 the problem as discovering dense clusters in highly
                 dynamic graphs. Despite many recent advances in graph
                 analysis, ours is the first technique to identify dense
                 clusters in massive and highly dynamic graphs in real
                 time. Given the characteristics of microblog streams,
                 in order to find clusters without missing any events,
                 we propose and exploit a novel graph property which we
                 call short-cycle property. Our algorithms find these
                 clusters efficiently in spite of rapid changes to the
                 microblog streams. Further we present a novel ranking
                 function to identify the important events. Besides
                 proving the correctness of our algorithms we show their
                 practical utility by evaluating them using real world
                 microblog data. These demonstrate our technique's
                 ability to discover, with high precision and recall,
                 emerging events in high intensity data streams in real
                 time. Many recent web applications create data which
                 can be represented as massive dynamic graphs. Our
                 technique can be easily extended to discover, in real
                 time, interesting patterns in such graphs.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Papapetrou:2012:SBQ,
  author =       "Odysseas Papapetrou and Minos Garofalakis and Antonios
                 Deligiannakis",
  title =        "Sketch-based querying of distributed sliding-window
                 data streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "992--1003",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "While traditional data-management systems focus on
                 evaluating single, ad-hoc queries over static data sets
                 in a centralized setting, several emerging applications
                 require (possibly, continuous) answers to queries on
                 dynamic data that is widely distributed and constantly
                 updated. Furthermore, such query answers often need to
                 discount data that is ``stale'', and operate solely on
                 a sliding window of recent data arrivals (e.g., data
                 updates occurring over the last 24 hours). Such
                 distributed data streaming applications mandate novel
                 algorithmic solutions that are both time- and
                 space-efficient (to manage high-speed data streams),
                 and also communication-efficient (to deal with physical
                 data distribution). In this paper, we consider the
                 problem of complex query answering over distributed,
                 high-dimensional data streams in the sliding-window
                 model. We introduce a novel sketching technique (termed
                 ECM-sketch) that allows effective summarization of
                 streaming data over both time-based and count-based
                 sliding windows with probabilistic accuracy guarantees.
                 Our sketch structure enables point as well as
                 inner-product queries, and can be employed to address a
                 broad range of problems, such as maintaining frequency
                 statistics, finding heavy hitters, and computing
                 quantiles in the sliding-window model. Focusing on
                 distributed environments, we demonstrate how
                 ECM-sketches of individual, local streams can be
                 composed to generate a (low-error) ECM-sketch summary
                 of the order-preserving aggregation of all streams;
                 furthermore, we show how ECM-sketches can be exploited
                 for continuous monitoring of sliding-window queries
                 over distributed streams. Our extensive experimental
                 study with two real-life data sets validates our
                 theoretical claims and verifies the effectiveness of
                 our techniques. To the best of our knowledge, ours is
                 the first work to address efficient, guaranteed-error
                 complex query answering over distributed data streams
                 in the sliding-window model.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Vo:2012:LSL,
  author =       "Hoang Tam Vo and Sheng Wang and Divyakant Agrawal and
                 Gang Chen and Beng Chin Ooi",
  title =        "{LogBase}: a scalable log-structured database system
                 in the cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1004--1015",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Numerous applications such as financial transactions
                 (e.g., stock trading) are write-heavy in nature. The
                 shift from reads to writes in web applications has also
                 been accelerating in recent years. Write-ahead-logging
                 is a common approach for providing recovery capability
                 while improving performance in most storage systems.
                 However, the separation of log and application data
                 incurs write overheads observed in write-heavy
                 environments and hence adversely affects the write
                 throughput and recovery time in the system. In this
                 paper, we introduce LogBase --- a scalable
                 log-structured database system that adopts log-only
                 storage for removing the write bottleneck and
                 supporting fast system recovery. It is designed to be
                 dynamically deployed on commodity clusters to take
                 advantage of elastic scaling property of cloud
                 environments. LogBase provides in-memory multiversion
                 indexes for supporting efficient access to data
                 maintained in the log. LogBase also supports
                 transactions that bundle read and write operations
                 spanning across multiple records. We implemented the
                 proposed system and compared it with HBase and a
                 disk-based log-structured record-oriented system
                 modeled after RAMCloud. The experimental results show
                 that LogBase is able to provide sustained write
                 throughput, efficient data access out of the cache, and
                 effective system recovery.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lu:2012:EPN,
  author =       "Wei Lu and Yanyan Shen and Su Chen and Beng Chin Ooi",
  title =        "Efficient processing of $k$ nearest neighbor joins
                 using {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1016--1027",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "k nearest neighbor join ($k$ NN join), designed to
                 find $k$ nearest neighbors from a dataset S for every
                 object in another dataset R, is a primitive operation
                 widely adopted by many data mining applications. As a
                 combination of the $k$ nearest neighbor query and the
                 join operation, $k$ NN join is an expensive operation.
                 Given the increasing volume of data, it is difficult to
                 perform a $k$ NN join on a centralized machine
                 efficiently. In this paper, we investigate how to
                 perform $k$ NN join using MapReduce which is a
                 well-accepted framework for data-intensive applications
                 over clusters of computers. In brief, the mappers
                 cluster objects into groups; the reducers perform the
                 $k$ NN join on each group of objects separately. We
                 design an effective mapping mechanism that exploits
                 pruning rules for distance filtering, and hence reduces
                 both the shuffling and computational costs. To reduce
                 the shuffling cost, we propose two approximate
                 algorithms to minimize the number of replicas.
                 Extensive experiments on our in-house cluster
                 demonstrate that our proposed methods are efficient,
                 robust and scalable.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Laptev:2012:EAR,
  author =       "Nikolay Laptev and Kai Zeng and Carlo Zaniolo",
  title =        "Early accurate results for advanced analytics on
                 {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1028--1039",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Approximate results based on samples often provide the
                 only way in which advanced analytical applications on
                 very massive data sets can satisfy their time and
                 resource constraints. Unfortunately, methods and tools
                 for the computation of accurate early results are
                 currently not supported in MapReduce-oriented systems
                 although these are intended for 'big data'. Therefore,
                 we proposed and implemented a non-parametric extension
                 of Hadoop which allows the incremental computation of
                 early results for arbitrary work-flows, along with
                 reliable on-line estimates of the degree of accuracy
                 achieved so far in the computation. These estimates are
                 based on a technique called bootstrapping that has been
                 widely employed in statistics and can be applied to
                 arbitrary functions and data distributions. In this
                 paper, we describe our Early Accurate Result Library
                 (EARL) for Hadoop that was designed to minimize the
                 changes required to the MapReduce framework. Various
                 tests of EARL of Hadoop are presented to characterize
                 the frequent situations where EARL can provide major
                 speed-ups over the current version of Hadoop.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2012:CCD,
  author =       "Xuan Liu and Meiyu Lu and Beng Chin Ooi and Yanyan
                 Shen and Sai Wu and Meihui Zhang",
  title =        "{CDAS}: a crowdsourcing data analytics system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1040--1051",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Some complex problems, such as image tagging and
                 natural language processing, are very challenging for
                 computers, where even state-of-the-art technology is
                 yet able to provide satisfactory accuracy. Therefore,
                 rather than relying solely on developing new and better
                 algorithms to handle such tasks, we look to the
                 crowdsourcing solution --- employing human
                 participation --- to make good the shortfall in current
                 technology. Crowdsourcing is a good supplement to many
                 computer tasks. A complex job may be divided into
                 computer-oriented tasks and human-oriented tasks, which
                 are then assigned to machines and humans respectively.
                 To leverage the power of crowdsourcing, we design and
                 implement a Crowdsourcing Data Analytics System, CDAS.
                 CDAS is a framework designed to support the deployment
                 of various crowdsourcing applications. The core part of
                 CDAS is a quality-sensitive answering model, which
                 guides the crowdsourcing engine to process and monitor
                 the human tasks. In this paper, we introduce the
                 principles of our quality-sensitive model. To satisfy
                 user required accuracy, the model guides the
                 crowdsourcing query engine for the design and
                 processing of the corresponding crowdsourcing jobs. It
                 provides an estimated accuracy for each generated
                 result based on the human workers' historical
                 performances. When verifying the quality of the result,
                 the model employs an online strategy to reduce waiting
                 time. To show the effectiveness of the model, we
                 implement and deploy two analytics jobs on CDAS, a
                 twitter sentiment analytics job and an image tagging
                 job. We use real Twitter and Flickr data as our queries
                 respectively. We compare our approaches with
                 state-of-the-art classification and image annotation
                 techniques. The results show that the human-assisted
                 methods can indeed achieve a much higher accuracy. By
                 embedding the quality-sensitive model into
                 crowdsourcing query engine, we effectively reduce the
                 processing cost while maintaining the required query
                 answer quality.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sachan:2012:MSS,
  author =       "Mayank Sachan and Arnab Bhattacharya",
  title =        "Mining statistically significant substrings using the
                 chi-square statistic",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1052--1063",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The problem of identification of statistically
                 significant patterns in a sequence of data has been
                 applied to many domains such as intrusion detection
                 systems, financial models, web-click records, automated
                 monitoring systems, computational biology, cryptology,
                 and text analysis. An observed pattern of events is
                 deemed to be statistically significant if it is
                 unlikely to have occurred due to randomness or chance
                 alone. We use the chi-square statistic as a
                 quantitative measure of statistical significance. Given
                 a string of characters generated from a memoryless
                 Bernoulli model, the problem is to identify the
                 substring for which the empirical distribution of
                 single letters deviates the most from the distribution
                 expected from the generative Bernoulli model. This
                 deviation is captured using the chi-square measure. The
                 most significant substring (MSS) of a string is thus
                 defined as the substring having the highest chi-square
                 value. Till date, to the best of our knowledge, there
                 does not exist any algorithm to find the MSS in better
                 than $O(n^2)$ time, where $n$ denotes the length of the
                 string. In this paper, we propose an algorithm to find
                 the most significant substring, whose running time is
                 $O(n^{3/2})$ with high probability. We also study some
                 variants of this problem such as finding the top-$t$
                 set, finding all substrings having chi-square greater
                 than a fixed threshold and finding the MSS among
                 substrings greater than a given length. We
                 experimentally demonstrate the asymptotic behavior of
                 the MSS on varying the string size and alphabet size.
                 We also describe some applications of our algorithm on
                 cryptology and real world data from finance and sports.
                 Finally, we compare our technique with the existing
                 heuristics for finding the MSS.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Albutiu:2012:MPS,
  author =       "Martina-Cezara Albutiu and Alfons Kemper and Thomas
                 Neumann",
  title =        "Massively parallel sort-merge joins in main memory
                 multi-core database systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1064--1075",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Two emerging hardware trends will dominate the
                 database system technology in the near future:
                 increasing main memory capacities of several TB per
                 server and massively parallel multi-core processing.
                 Many algorithmic and control techniques in current
                 database technology were devised for disk-based systems
                 where I/O dominated the performance. In this work we
                 take a new look at the well-known sort-merge join
                 which, so far, has not been in the focus of research in
                 scalable massively parallel multi-core data processing
                 as it was deemed inferior to hash joins. We devise a
                 suite of new massively parallel sort-merge (MPSM) join
                 algorithms that are based on partial partition-based
                 sorting. Contrary to classical sort-merge joins, our
                 MPSM algorithms do not rely on a hard to parallelize
                 final merge step to create one complete sort order.
                 Rather they work on the independently created runs in
                 parallel. This way our MPSM algorithms are NUMA-affine
                 as all the sorting is carried out on local memory
                 partitions. An extensive experimental evaluation on a
                 modern 32-core machine with one TB of main memory
                 proves the competitive performance of MPSM on large
                 main memory databases with billions of objects. It
                 scales (almost) linearly in the number of employed
                 cores and clearly outperforms competing hash join
                 proposals --- in particular it outperforms the
                 ``cutting-edge'' Vectorwise parallel query engine by a
                 factor of four.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Luo:2012:HDH,
  author =       "Tian Luo and Rubao Lee and Michael Mesnier and Feng
                 Chen and Xiaodong Zhang",
  title =        "{hStorage-DB}: heterogeneity-aware data management to
                 exploit the full capability of hybrid storage systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "10",
  pages =        "1076--1087",
  month =        jun,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:13 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As storage systems become increasingly heterogeneous
                 and complex, it adds burdens on DBAs, causing
                 suboptimal performance even after a lot of human
                 efforts have been made. In addition, existing
                 monitoring-based storage management by access pattern
                 detections has difficulties to handle workloads that
                 are highly dynamic and concurrent. To achieve high
                 performance by best utilizing heterogeneous storage
                 devices, we have designed and implemented a
                 heterogeneity-aware software framework for DBMS storage
                 management called hStorage-DB, where semantic
                 information that is critical for storage I/O is
                 identified and passed to the storage manager. According
                 to the collected semantic information, requests are
                 classified into different types. Each type is assigned
                 a proper QoS policy supported by the underlying storage
                 system, so that every request will be served with a
                 suitable storage device. With hStorage-DB, we can well
                 utilize semantic information that cannot be detected
                 through data access monitoring but is particularly
                 important for a hybrid storage system. To show the
                 effectiveness of hStorage-DB, we have implemented a
                 system prototype that consists of an I/O request
                 classification enabled DBMS, and a hybrid storage
                 system that is organized into a two-level caching
                 hierarchy. Our performance evaluation shows that
                 hStorage-DB can automatically make proper decisions for
                 data allocation in different storage devices and make
                 substantial performance improvements in a
                 cost-efficient way.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Choi:2012:SAM,
  author =       "Dong-Wan Choi and Chin-Wan Chung and Yufei Tao",
  title =        "A scalable algorithm for maximizing range sum in
                 spatial databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1088--1099",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper investigates the MaxRS problem in spatial
                 databases. Given a set O of weighted points and a
                 rectangular region r of a given size, the goal of the
                 MaxRS problem is to find a location of r such that the
                 sum of the weights of all the points covered by r is
                 maximized. This problem is useful in many
                 location-based applications such as finding the best
                 place for a new franchise store with a limited delivery
                 range and finding the most attractive place for a
                 tourist with a limited reachable range. However, the
                 problem has been studied mainly in theory,
                 particularly, in computational geometry. The existing
                 algorithms from the computational geometry community
                 are in-memory algorithms which do not guarantee the
                 scalability. In this paper, we propose a scalable
                 external-memory algorithm (ExactMaxRS) for the MaxRS
                 problem, which is optimal in terms of the I/O
                 complexity. Furthermore, we propose an approximation
                 algorithm (ApproxMaxCRS) for the MaxCRS problem that is
                 a circle version of the MaxRS problem. We prove the
                 correctness and optimality of the ExactMaxRS algorithm
                 along with the approximation bound of the ApproxMaxCRS
                 algorithm. From extensive experimental results, we show
                 that the ExactMaxRS algorithm is two orders of
                 magnitude faster than methods adapted from existing
                 algorithms, and the approximation bound in practice is
                 much better than the theoretical bound of the
                 ApproxMaxCRS algorithm.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Aly:2012:SQT,
  author =       "Ahmed M. Aly and Walid G. Aref and Mourad Ouzzani",
  title =        "Spatial queries with two {kNN} predicates",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1100--1111",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The widespread use of location-aware devices has led
                 to countless location-based services in which a user
                 query can be arbitrarily complex, i.e., one that embeds
                 multiple spatial selection and join predicates. Amongst
                 these predicates, the $k$-Nearest-Neighbor ($k$ NN)
                 predicate stands as one of the most important and
                 widely used predicates. Unlike related research, this
                 paper goes beyond the optimization of queries with
                 single $k$ NN predicates, and shows how queries with
                 two $k$ NN predicates can be optimized. In particular,
                 the paper addresses the optimization of queries with:
                 (i) two $k$ NN-select predicates, (ii) two $k$ NN-join
                 predicates, and (iii) one $k$ NN-join predicate and one
                 $k$ NN-select predicate. For each type of queries,
                 conceptually correct query evaluation plans (QEPs) and
                 new algorithms that optimize the query execution time
                 are presented. Experimental results demonstrate that
                 the proposed algorithms outperform the conceptually
                 correct QEPs by orders of magnitude.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sheng:2012:OAC,
  author =       "Cheng Sheng and Nan Zhang and Yufei Tao and Xin Jin",
  title =        "Optimal algorithms for crawling a hidden database in
                 the web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1112--1123",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A hidden database refers to a dataset that an
                 organization makes accessible on the web by allowing
                 users to issue queries through a search interface. In
                 other words, data acquisition from such a source is not
                 by following static hyper-links. Instead, data are
                 obtained by querying the interface, and reading the
                 result page dynamically generated. This, with other
                 facts such as the interface may answer a query only
                 partially, has prevented hidden databases from being
                 crawled effectively by existing search engines. This
                 paper remedies the problem by giving algorithms to
                 extract all the tuples from a hidden database. Our
                 algorithms are provably efficient, namely, they
                 accomplish the task by performing only a small number
                 of queries, even in the worst case. We also establish
                 theoretical results indicating that these algorithms
                 are asymptotically optimal --- i.e., it is impossible
                 to improve their efficiency by more than a constant
                 factor. The derivation of our upper and lower bound
                 results reveals significant insight into the
                 characteristics of the underlying problem. Extensive
                 experiments confirm the proposed techniques work very
                 well on all the real datasets examined.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Qin:2012:DTR,
  author =       "Lu Qin and Jeffrey Xu Yu and Lijun Chang",
  title =        "Diversifying top-$k$ results",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1124--1135",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Top-$k$ query processing finds a list of $k$ results
                 that have largest scores w.r.t the user given query,
                 with the assumption that all the $k$ results are
                 independent to each other. In practice, some of the
                 top-$k$ results returned can be very similar to each
                 other. As a result some of the top-$k$ results returned
                 are redundant. In the literature, diversified top-$k$
                 search has been studied to return $k$ results that take
                 both score and diversity into consideration. Most
                 existing solutions on diversified top-$k$ search assume
                 that scores of all the search results are given, and
                 some works solve the diversity problem on a specific
                 problem and can hardly be extended to general cases. In
                 this paper, we study the diversified top-$k$ search
                 problem. We define a general diversified top- $k$
                 search problem that only considers the similarity of
                 the search results themselves. We propose a framework,
                 such that most existing solutions for top- $k$ query
                 processing can be extended easily to handle diversified
                 top-$k$ search, by simply applying three new functions,
                 a sufficient stop condition sufficient(), a necessary
                 stop condition necessary(), and an algorithm for
                 diversified top-$k$ search on the current set of
                 generated results, div-search-current(). We propose
                 three new algorithms, namely, div-astar, div-dp, and
                 div-cut to solve the div-search-current() problem.
                 div-astar is an A* based algorithm, div-dp is an
                 algorithm that decomposes the results into components
                 which are searched using div-astar independently and
                 combined using dynamic programming. div-cut further
                 decomposes the current set of generated results using
                 cut points and combines the results using sophisticated
                 operations. We conducted extensive performance studies
                 using two real datasets, enwiki and reuters. Our
                 div-cut algorithm finds the optimal solution for
                 diversified top-$k$ search problem in seconds even for
                 $k$ as large as 2, 000.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2012:KAO,
  author =       "Xin Cao and Lisi Chen and Gao Cong and Xiaokui Xiao",
  title =        "Keyword-aware optimal route search",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1136--1147",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Identifying a preferable route is an important problem
                 that finds applications in map services. When a user
                 plans a trip within a city, the user may want to find
                 ``a most popular route such that it passes by shopping
                 mall, restaurant, and pub, and the travel time to and
                 from his hotel is within 4 hours.'' However, none of
                 the algorithms in the existing work on route planning
                 can be used to answer such queries. Motivated by this,
                 we define the problem of keyword-aware optimal route
                 query, denoted by KOR, which is to find an optimal
                 route such that it covers a set of user-specified
                 keywords, a specified budget constraint is satisfied,
                 and an objective score of the route is optimal. The
                 problem of answering KOR queries is NP-hard. We devise
                 an approximation algorithm OSScaling with provable
                 approximation bounds. Based on this algorithm, another
                 more efficient approximation algorithm BucketBound is
                 proposed. We also design a greedy approximation
                 algorithm. Results of empirical studies show that all
                 the proposed algorithms are capable of answering KOR
                 queries efficiently, while the BucketBound and Greedy
                 algorithms run faster. The empirical studies also offer
                 insight into the accuracy of the proposed algorithms.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cautis:2012:AQU,
  author =       "Bogdan Cautis and Evgeny Kharlamov",
  title =        "Answering queries using views over probabilistic
                 {XML}: complexity and tractability",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1148--1159",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We study the complexity of query answering using views
                 in a probabilistic XML setting, identifying large
                 classes of XPath queries --- with child and descendant
                 navigation and predicates --- for which there are
                 efficient (PTime) algorithms. We consider this problem
                 under the two possible semantics for XML query results:
                 with persistent node identifiers and in their absence.
                 Accordingly, we consider rewritings that can exploit a
                 single view, by means of compensation, and rewritings
                 that can use multiple views, by means of intersection.
                 Since in a probabilistic setting queries return answers
                 with probabilities, the problem of rewriting goes
                 beyond the classic one of retrieving XML answers from
                 views. For both semantics of XML queries, we show that,
                 even when XML answers can be retrieved from views,
                 their probabilities may not be computable. For
                 rewritings that use only compensation, we describe a
                 PTime decision procedure, based on easily verifiable
                 criteria that distinguish between the feasible cases
                 --- when probabilistic XML results are computable ---
                 and the unfeasible ones. For rewritings that can use
                 multiple views, with compensation and intersection, we
                 identify the most permissive conditions that make
                 probabilistic rewriting feasible, and we describe an
                 algorithm that is sound in general, and becomes
                 complete under fairly permissive restrictions, running
                 in PTime modulo worst-case exponential time equivalence
                 tests. This is the best we can hope for since
                 intersection makes query equivalence intractable
                 already over deterministic data. Our algorithm runs in
                 PTime whenever deterministic rewritings can be found in
                 PTime.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jha:2012:PDM,
  author =       "Abhay Jha and Dan Suciu",
  title =        "Probabilistic databases with {MarkoViews}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1160--1171",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Most of the work on query evaluation in probabilistic
                 databases has focused on the simple tuple-independent
                 data model, where tuples are independent random events.
                 Several efficient query evaluation techniques exists in
                 this setting, such as safe plans, algorithms based on
                 OBDDs, tree-decomposition and a variety of
                 approximation algorithms. However, complex data
                 analytics tasks often require complex correlations, and
                 query evaluation then is significantly more expensive,
                 or more restrictive. In this paper, we propose MVDB as
                 a framework both for representing complex correlations
                 and for efficient query evaluation. An MVDB specifies
                 correlations by views, called MarkoViews, on the
                 probabilistic relations and declaring the weights of
                 the view's outputs. An MVDB is a (very large) Markov
                 Logic Network. We make two sets of contributions.
                 First, we show that query evaluation on an MVDB is
                 equivalent to evaluating a Union of Conjunctive
                 Query(UCQ) over a tuple-independent database. The
                 translation is exact (thus allowing the techniques
                 developed for tuple independent databases to be carried
                 over to MVDB), yet it is novel and quite non-obvious
                 (some resulting probabilities may be negative!). This
                 translation in itself though may not lead to much gain
                 since the translated query gets complicated as we try
                 to capture more correlations. Our second contribution
                 is to propose a new query evaluation strategy that
                 exploits offline compilation to speed up online query
                 evaluation. Here we utilize and extend our prior work
                 on compilation of UCQ. We validate experimentally our
                 techniques on a large probabilistic database with
                 MarkoViews inferred from the DBLP data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mamouras:2012:CSC,
  author =       "Konstantinos Mamouras and Sigal Oren and Lior Seeman
                 and Lucja Kot and Johannes Gehrke",
  title =        "The complexity of social coordination",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1172--1183",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Coordination is a challenging everyday task; just
                 think of the last time you organized a party or a
                 meeting involving several people. As a growing part of
                 our social and professional life goes online, an
                 opportunity for an improved coordination process
                 arises. Recently, Gupta et al. proposed entangled
                 queries as a declarative abstraction for data-driven
                 coordination, where the difficulty of the coordination
                 task is shifted from the user to the database.
                 Unfortunately, evaluating entangled queries is very
                 hard, and thus previous work considered only a
                 restricted class of queries that satisfy safety (the
                 coordination partners are fixed) and uniqueness (all
                 queries need to be satisfied). In this paper we
                 significantly extend the class of feasible entangled
                 queries beyond uniqueness and safety. First, we show
                 that we can simply drop uniqueness and still
                 efficiently evaluate a set of safe entangled queries.
                 Second, we show that as long as all users coordinate on
                 the same set of attributes, we can give an efficient
                 algorithm for coordination even if the set of queries
                 does not satisfy safety. In an experimental evaluation
                 we show that our algorithms are feasible for a wide
                 spectrum of coordination scenarios.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2012:EMW,
  author =       "Xiaofei Zhang and Lei Chen and Min Wang",
  title =        "Efficient multi-way theta-join processing using
                 {MapReduce}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1184--1195",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Multi-way Theta-join queries are powerful in
                 describing complex relations and therefore widely
                 employed in real practices. However, existing solutions
                 from traditional distributed and parallel databases for
                 multi-way Theta-join queries cannot be easily extended
                 to fit a shared-nothing distributed computing paradigm,
                 which is proven to be able to support OLAP applications
                 over immense data volumes. In this work, we study the
                 problem of efficient processing of multi-way Theta-join
                 queries using MapReduce from a cost-effective
                 perspective. Although there have been some works using
                 the (key, value) pair-based programming model to
                 support join operations, efficient processing of
                 multi-way Theta-join queries has never been fully
                 explored. The substantial challenge lies in, given a
                 number of processing units (that can run Map or Reduce
                 tasks), mapping a multi-way Theta-join query to a
                 number of MapReduce jobs and having them executed in a
                 well scheduled sequence, such that the total processing
                 time span is minimized. Our solution mainly includes
                 two parts: (1) cost metrics for both single MapReduce
                 job and a number of MapReduce jobs executed in a
                 certain order; (2) the efficient execution of a
                 chain-typed Theta-join with only one MapReduce job.
                 Comparing with the query evaluation strategy proposed
                 in [23] and the widely adopted Pig Latin and Hive SQL
                 solutions, our method achieves significant improvement
                 of the join processing efficiency.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lim:2012:STB,
  author =       "Harold Lim and Herodotos Herodotou and Shivnath Babu",
  title =        "{Stubby}: a transformation-based optimizer for
                 {MapReduce} workflows",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1196--1207",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "There is a growing trend of performing analysis on
                 large datasets using workflows composed of MapReduce
                 jobs connected through producer-consumer relationships
                 based on data. This trend has spurred the development
                 of a number of interfaces---ranging from program-based
                 to query-based interfaces---for generating MapReduce
                 workflows. Studies have shown that the gap in
                 performance can be quite large between optimized and
                 unoptimized workflows. However, automatic cost-based
                 optimization of MapReduce workflows remains a challenge
                 due to the multitude of interfaces, large size of the
                 execution plan space, and the frequent unavailability
                 of all types of information needed for optimization. We
                 introduce a comprehensive plan space for MapReduce
                 workflows generated by popular workflow generators. We
                 then propose Stubby, a cost-based optimizer that
                 searches selectively through the subspace of the full
                 plan space that can be enumerated correctly and costed
                 based on the information available in any given
                 setting. Stubby enumerates the plan space based on
                 plan-to-plan transformations and an efficient search
                 algorithm. Stubby is designed to be extensible to new
                 interfaces and new types of optimizations, which is a
                 desirable feature given how rapidly MapReduce systems
                 are evolving. Stubby's efficiency and effectiveness
                 have been evaluated using representative workflows from
                 many domains.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bao:2012:LWV,
  author =       "Zhuowei Bao and Susan B. Davidson and Tova Milo",
  title =        "Labeling workflow views with fine-grained
                 dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1208--1219",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper considers the problem of efficiently
                 answering reachability queries over views of provenance
                 graphs, derived from executions of workflows that may
                 include recursion. Such views include composite modules
                 and model fine-grained dependencies between module
                 inputs and outputs. A novel view-adaptive dynamic
                 labeling scheme is developed for efficient query
                 evaluation, in which view specifications are labeled
                 statically (i.e. as they are created) and data items
                 are labeled dynamically as they are produced during a
                 workflow execution. Although the combination of
                 fine-grained dependencies and recursive workflows
                 entail, in general, long (linear-size) data labels, we
                 show that for a large natural class of workflows and
                 views, labels are compact (logarithmic-size) and
                 reachability queries can be evaluated in constant time.
                 Experimental results demonstrate the benefit of this
                 approach over the state-of-the-art technique when
                 applied for labeling multiple views.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Szlichta:2012:FOD,
  author =       "Jaroslaw Szlichta and Parke Godfrey and Jarek Gryz",
  title =        "Fundamentals of order dependencies",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1220--1231",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Dependencies have played a significant role in
                 database design for many years. They have also been
                 shown to be useful in query optimization. In this
                 paper, we discuss dependencies between
                 lexicographically ordered sets of tuples. We introduce
                 formally the concept of order dependency and present a
                 set of axioms (inference rules) for them. We show how
                 query rewrites based on these axioms can be used for
                 query optimization. We present several interesting
                 theorems that can be derived using the inference rules.
                 We prove that functional dependencies are subsumed by
                 order dependencies and that our set of axioms for order
                 dependencies is sound and complete.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bakibayev:2012:FQE,
  author =       "Nurzhan Bakibayev and Dan Olteanu and Jakub
                 Z{\'a}vodn{\'y}",
  title =        "{FDB}: a query engine for factorised relational
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1232--1243",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Factorised databases are relational databases that use
                 compact factorised representations at the physical
                 layer to reduce data redundancy and boost query
                 performance. This paper introduces FDB, an in-memory
                 query engine for select-project-join queries on
                 factorised databases. Key components of FDB are novel
                 algorithms for query optimisation and evaluation that
                 exploit the succinctness brought by data factorisation.
                 Experiments show that for data sets with many-to-many
                 relationships FDB can outperform relational engines by
                 orders of magnitude.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2012:OAW,
  author =       "Yu Cao and Chee-Yong Chan and Jie Li and Kian-Lee
                 Tan",
  title =        "Optimization of analytic window functions",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1244--1255",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Analytic functions represent the state-of-the-art way
                 of performing complex data analysis within a single SQL
                 statement. In particular, an important class of
                 analytic functions that has been frequently used in
                 commercial systems to support OLAP and decision support
                 applications is the class of window functions. A window
                 function returns for each input tuple a value derived
                 from applying a function over a window of neighboring
                 tuples. However, existing window function evaluation
                 approaches are based on a naive sorting scheme. In this
                 paper, we study the problem of optimizing the
                 evaluation of window functions. We propose several
                 efficient techniques, and identify optimization
                 opportunities that allow us to optimize the evaluation
                 of a set of window functions. We have integrated our
                 scheme into PostgreSQL. Our comprehensive experimental
                 study on the TPC-DS datasets as well as synthetic
                 datasets and queries demonstrate significant speedup
                 over existing approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hueske:2012:OBB,
  author =       "Fabian Hueske and Mathias Peters and Matthias J. Sax
                 and Astrid Rheinl{\"a}nder and Rico Bergmann and
                 Aljoscha Krettek and Kostas Tzoumas",
  title =        "Opening the black boxes in data flow optimization",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1256--1267",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Many systems for big data analytics employ a data flow
                 abstraction to define parallel data processing tasks.
                 In this setting, custom operations expressed as
                 user-defined functions are very common. We address the
                 problem of performing data flow optimization at this
                 level of abstraction, where the semantics of operators
                 are not known. Traditionally, query optimization is
                 applied to queries with known algebraic semantics. In
                 this work, we find that a handful of properties, rather
                 than a full algebraic specification, suffice to
                 establish reordering conditions for data processing
                 operators. We show that these properties can be
                 accurately estimated for black box operators by
                 statically analyzing the general-purpose code of their
                 user-defined functions. We design and implement an
                 optimizer for parallel data flows that does not assume
                 knowledge of semantics or algebraic properties of
                 operators. Our evaluation confirms that the optimizer
                 can apply common rewritings such as selection
                 reordering, bushy join-order enumeration, and limited
                 forms of aggregation push-down, hence yielding similar
                 rewriting power as modern relational DBMS optimizers.
                 Moreover, it can optimize the operator order of
                 nonrelational data flows, a unique feature among
                 today's systems.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ewen:2012:SFI,
  author =       "Stephan Ewen and Kostas Tzoumas and Moritz Kaufmann
                 and Volker Markl",
  title =        "Spinning fast iterative data flows",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1268--1279",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Parallel dataflow systems are a central part of most
                 analytic pipelines for big data. The iterative nature
                 of many analysis and machine learning algorithms,
                 however, is still a challenge for current systems.
                 While certain types of bulk iterative algorithms are
                 supported by novel dataflow frameworks, these systems
                 cannot exploit computational dependencies present in
                 many algorithms, such as graph algorithms. As a result,
                 these algorithms are inefficiently executed and have
                 led to specialized systems based on other paradigms,
                 such as message passing or shared memory. We propose a
                 method to integrate incremental iterations, a form of
                 workset iterations, with parallel dataflows. After
                 showing how to integrate bulk iterations into a
                 dataflow system and its optimizer, we present an
                 extension to the programming model for incremental
                 iterations. The extension alleviates for the lack of
                 mutable state in dataflows and allows for exploiting
                 the sparse computational dependencies inherent in many
                 iterative algorithms. The evaluation of a prototypical
                 implementation shows that those aspects lead to up to
                 two orders of magnitude speedup in algorithm runtime,
                 when exploited. In our experiments, the improved
                 dataflow system is highly competitive with specialized
                 systems while maintaining a transparent and unified
                 dataflow abstraction.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Mihaylov:2012:RRD,
  author =       "Svilen R. Mihaylov and Zachary G. Ives and Sudipto
                 Guha",
  title =        "{REX}: recursive, delta-based data-centric
                 computation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1280--1291",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In today's Web and social network environments, query
                 workloads include ad hoc and OLAP queries, as well as
                 iterative algorithms that analyze data relationships
                 (e.g., link analysis, clustering, learning). Modern
                 DBMSs support ad hoc and OLAP queries, but most are not
                 robust enough to scale to large clusters. Conversely,
                 ``cloud'' platforms like MapReduce execute chains of
                 batch tasks across clusters in a fault tolerant way,
                 but have too much overhead to support ad hoc queries.
                 Moreover, both classes of platform incur significant
                 overhead in executing iterative data analysis
                 algorithms. Most such iterative algorithms repeatedly
                 refine portions of their answers, until some
                 convergence criterion is reached. However, general
                 cloud platforms typically must reprocess all data in
                 each step. DBMSs that support recursive SQL are more
                 efficient in that they propagate only the changes in
                 each step --- but they still accumulate each
                 iteration's state, even if it is no longer useful.
                 User-defined functions are also typically harder to
                 write for DBMSs than for cloud platforms. We seek to
                 unify the strengths of both styles of platforms, with a
                 focus on supporting iterative computations in which
                 changes, in the form of deltas, are propagated from
                 iteration to iteration, and state is efficiently
                 updated in an extensible way. We present a programming
                 model oriented around deltas, describe how we execute
                 and optimize such programs in our REX runtime system,
                 and validate that our platform also handles failures
                 gracefully. We experimentally validate our techniques,
                 and show speedups over the competing methods ranging
                 from 2.5 to nearly 100 times.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheng:2012:KRW,
  author =       "James Cheng and Zechao Shang and Hong Cheng and Haixun
                 Wang and Jeffrey Xu Yu",
  title =        "{K}-reach: who is in your small world",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1292--1303",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We study the problem of answering $k$-hop reachability
                 queries in a directed graph, i.e., whether there exists
                 a directed path of length k, from a source query vertex
                 to a target query vertex in the input graph. The
                 problem of $k$-hop reachability is a general problem of
                 the classic reachability (where $k = \infty$). Existing
                 indexes for processing classic reachability queries, as
                 well as for processing shortest path queries, are not
                 applicable or not efficient for processing $k$-hop
                 reachability queries. We propose an index for
                 processing $k$-hop reachability queries, which is
                 simple in design and efficient to construct. Our
                 experimental results on a wide range of real datasets
                 show that our index is more efficient than the
                 state-of-the-art indexes even for processing classic
                 reachability queries, for which these indexes are
                 primarily designed. We also show that our index is
                 efficient in answering $k$-hop reachability queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Fan:2012:PGD,
  author =       "Wenfei Fan and Xin Wang and Yinghui Wu",
  title =        "Performance guarantees for distributed reachability
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1304--1316",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In the real world a graph is often fragmented and
                 distributed across different sites. This highlights the
                 need for evaluating queries on distributed graphs. This
                 paper proposes distributed evaluation algorithms for
                 three classes of queries: reachability for determining
                 whether one node can reach another, bounded
                 reachability for deciding whether there exists a path
                 of a bounded length between a pair of nodes, and
                 regular reachability for checking whether there exists
                 a path connecting two nodes such that the node labels
                 on the path form a string in a given regular
                 expression. We develop these algorithms based on
                 partial evaluation, to explore parallel computation.
                 When evaluating a query Q on a distributed graph G, we
                 show that these algorithms possess the following
                 performance guarantees, no matter how G is fragmented
                 and distributed: (1) each site is visited only once;
                 (2) the total network traffic is determined by the size
                 of Q and the fragmentation of G, independent of the
                 size of G; and (3) the response time is decided by the
                 largest fragment of G rather than the entire G. In
                 addition, we show that these algorithms can be readily
                 implemented in the MapReduce framework. Using synthetic
                 and real-life data, we experimentally verify that these
                 algorithms are scalable on large graphs, regardless of
                 how the graphs are distributed.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chubak:2012:EIQ,
  author =       "Pirooz Chubak and Davood Rafiei",
  title =        "Efficient indexing and querying over syntactically
                 annotated trees",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1316--1327",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Natural language text corpora are often available as
                 sets of syntactically parsed trees. A wide range of
                 expressive tree queries are possible over such parsed
                 trees that open a new avenue in searching over natural
                 language text. They not only allow for querying roles
                 and relationships within sentences, but also improve
                 search effectiveness compared to flat keyword queries.
                 One major drawback of current systems supporting
                 querying over parsed text is the performance of
                 evaluating queries over large data. In this paper we
                 propose a novel indexing scheme over unique subtrees as
                 index keys. We also propose a novel root-split coding
                 scheme that stores subtree structural information only
                 partially, thus reducing index size and improving
                 querying performance. Our extensive set of experiments
                 show that root-split coding reduces the index size of
                 any interval coding which stores individual node
                 numbers by a factor of 50\% to 80\%, depending on the
                 sizes of subtrees indexed. Moreover, We show that our
                 index using root-split coding, outperforms previous
                 approaches by at least an order of magnitude in terms
                 of the response time of queries.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Barany:2012:QGN,
  author =       "Vince B{\'a}r{\'a}ny and Balder ten Cate and Martin
                 Otto",
  title =        "Queries with guarded negation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1328--1339",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A well-established and fundamental insight in database
                 theory is that negation (also known as complementation)
                 tends to make queries difficult to process and
                 difficult to reason about. Many basic problems are
                 decidable and admit practical algorithms in the case of
                 unions of conjunctive queries, but become difficult or
                 even undecidable when queries are allowed to contain
                 negation. Inspired by recent results in finite model
                 theory, we consider a restricted form of negation,
                 guarded negation. We introduce a fragment of SQL,
                 called GN-SQL, as well as a fragment of Datalog with
                 stratified negation, called GN-Datalog, that allow only
                 guarded negation, and we show that these query
                 languages are computationally well behaved, in terms of
                 testing query containment, query evaluation, open-world
                 query answering, and boundedness. GN-SQL and GN-Datalog
                 subsume a number of well known query languages and
                 constraint languages, such as unions of conjunctive
                 queries, monadic Datalog, and frontier-guarded tgds. In
                 addition, an analysis of standard benchmark workloads
                 shows that many uses of negation in SQL in practice are
                 guarded.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2012:PFI,
  author =       "Ninghui Li and Wahbeh Qardaji and Dong Su and Jianneng
                 Cao",
  title =        "{PrivBasis}: frequent itemset mining with differential
                 privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1340--1351",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The discovery of frequent itemsets can serve valuable
                 economic and research purposes. Releasing discovered
                 frequent itemsets, however, presents privacy
                 challenges. In this paper, we study the problem of how
                 to perform frequent itemset mining on transaction
                 databases while satisfying differential privacy. We
                 propose an approach, called PrivBasis, which leverages
                 a novel notion called basis sets. A $\theta$-basis set
                 has the property that any itemset with frequency higher
                 than $\theta$ is a subset of some basis. We introduce
                 algorithms for privately constructing a basis set and
                 then using it to find the most frequent itemsets.
                 Experiments show that our approach greatly outperforms
                 the current state of the art.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yuan:2012:LRM,
  author =       "Ganzhao Yuan and Zhenjie Zhang and Marianne Winslett
                 and Xiaokui Xiao and Yin Yang and Zhifeng Hao",
  title =        "Low-rank mechanism: optimizing batch queries under
                 differential privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1352--1363",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Differential privacy is a promising privacy-preserving
                 paradigm for statistical query processing over
                 sensitive data. It works by injecting random noise into
                 each query result, such that it is provably hard for
                 the adversary to infer the presence or absence of any
                 individual record from the published noisy results. The
                 main objective in differentially private query
                 processing is to maximize the accuracy of the query
                 results, while satisfying the privacy guarantees.
                 Previous work, notably the matrix mechanism [16], has
                 suggested that processing a batch of correlated queries
                 as a whole can potentially achieve considerable
                 accuracy gains, compared to answering them
                 individually. However, as we point out in this paper,
                 the matrix mechanism is mainly of theoretical interest;
                 in particular, several inherent problems in its design
                 limit its accuracy in practice, which almost never
                 exceeds that of na{\"\i}ve methods. In fact, we are not
                 aware of any existing solution that can effectively
                 optimize a query batch under differential privacy.
                 Motivated by this, we propose the Low-Rank Mechanism
                 (LRM), the first practical differentially private
                 technique for answering batch queries with high
                 accuracy, based on a low rank approximation of the
                 workload matrix. We prove that the accuracy provided by
                 LRM is close to the theoretical lower bound for any
                 mechanism to answer a batch of queries under
                 differential privacy. Extensive experiments using real
                 data demonstrate that LRM consistently outperforms
                 state-of-the-art query processing solutions under
                 differential privacy, by large margins.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhang:2012:FMR,
  author =       "Jun Zhang and Zhenjie Zhang and Xiaokui Xiao and Yin
                 Yang and Marianne Winslett",
  title =        "Functional mechanism: regression analysis under
                 differential privacy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1364--1375",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "$\epsilon$-differential privacy is the
                 state-of-the-art model for releasing sensitive
                 information while protecting privacy. Numerous methods
                 have been proposed to enforce $\epsilon$-differential
                 privacy in various analytical tasks, e.g., regression
                 analysis. Existing solutions for regression analysis,
                 however, are either limited to non-standard types of
                 regression or unable to produce accurate regression
                 results. Motivated by this, we propose the Functional
                 Mechanism, a differentially private method designed for
                 a large class of optimization-based analyses. The main
                 idea is to enforce $\epsilon$-differential privacy by
                 perturbing the objective function of the optimization
                 problem, rather than its results. As case studies, we
                 apply the functional mechanism to address two most
                 widely used regression models, namely, linear
                 regression and logistic regression. Both theoretical
                 analysis and thorough experimental evaluations show
                 that the functional mechanism is highly effective and
                 efficient, and it significantly outperforms existing
                 solutions.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Boldi:2012:IUG,
  author =       "Paolo Boldi and Francesco Bonchi and Aristides Gionis
                 and Tamir Tassa",
  title =        "Injecting uncertainty in graphs for identity
                 obfuscation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1376--1387",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Data collected nowadays by social-networking
                 applications create fascinating opportunities for
                 building novel services, as well as expanding our
                 understanding about social structures and their
                 dynamics. Unfortunately, publishing social-network
                 graphs is considered an ill-advised practice due to
                 privacy concerns. To alleviate this problem, several
                 anonymization methods have been proposed, aiming at
                 reducing the risk of a privacy breach on the published
                 data, while still allowing to analyze them and draw
                 relevant conclusions. In this paper we introduce a new
                 anonymization approach that is based on injecting
                 uncertainty in social graphs and publishing the
                 resulting uncertain graphs. While existing approaches
                 obfuscate graph data by adding or removing edges
                 entirely, we propose using a finer-grained perturbation
                 that adds or removes edges partially: this way we can
                 achieve the same desired level of obfuscation with
                 smaller changes in the data, thus maintaining higher
                 utility. Our experiments on real-world networks confirm
                 that at the same level of identity obfuscation our
                 method provides higher usefulness than existing
                 randomized methods that publish standard graphs.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2012:PMR,
  author =       "Jianneng Cao and Panagiotis Karras",
  title =        "Publishing microdata with a robust privacy guarantee",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1388--1399",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Today, the publication of microdata poses a privacy
                 threat. Vast research has striven to define the privacy
                 condition that microdata should satisfy before it is
                 released, and devise algorithms to anonymize the data
                 so as to achieve this condition. Yet, no method
                 proposed to date explicitly bounds the percentage of
                 information an adversary gains after seeing the
                 published data for each sensitive value therein. This
                 paper introduces $\beta$-likeness, an appropriately
                 robust privacy model for microdata anonymization, along
                 with two anonymization schemes designed therefore, the
                 one based on generalization, and the other based on
                 perturbation. Our model postulates that an adversary's
                 confidence on the likelihood of a certain
                 sensitive-attribute (SA) value should not increase, in
                 relative difference terms, by more than a predefined
                 threshold. Our techniques aim to satisfy a given
                 $\beta$ threshold with little information loss. We
                 experimentally demonstrate that (i) our model provides
                 an effective privacy guarantee in a way that
                 predecessor models cannot, (ii) our generalization
                 scheme is more effective and efficient in its task than
                 methods adapting algorithms for the $k$-anonymity
                 model, and (iii) our perturbation method outperforms a
                 baseline approach. Moreover, we discuss in detail the
                 resistance of our model and methods to attacks proposed
                 in previous research.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Guan:2012:MTE,
  author =       "Ziyu Guan and Xifeng Yan and Lance M. Kaplan",
  title =        "Measuring two-event structural correlations on
                 graphs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1400--1411",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Real-life graphs usually have various kinds of events
                 happening on them, e.g., product purchases in online
                 social networks and intrusion alerts in computer
                 networks. The occurrences of events on the same graph
                 could be correlated, exhibiting either attraction or
                 repulsion. Such structural correlations can reveal
                 important relationships between different events.
                 Unfortunately, correlation relationships on graph
                 structures are not well studied and cannot be captured
                 by traditional measures. In this work, we design a
                 novel measure for assessing two-event structural
                 correlations on graphs. Given the occurrences of two
                 events, we choose uniformly a sample of ``reference
                 nodes'' from the vicinity of all event nodes and employ
                 the Kendall's $\tau$ rank correlation measure to
                 compute the average concordance of event density
                 changes. Significance can be efficiently assessed by
                 $\tau$'s nice property of being asymptotically normal
                 under the null hypothesis. In order to compute the
                 measure in large scale networks, we develop a scalable
                 framework using different sampling strategies. The
                 complexity of these strategies is analyzed. Experiments
                 on real graph datasets with both synthetic and real
                 events demonstrate that the proposed framework is not
                 only efficacious, but also efficient and scalable.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jestes:2012:RLT,
  author =       "Jeffrey Jestes and Jeff M. Phillips and Feifei Li and
                 Mingwang Tang",
  title =        "Ranking large temporal data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1412--1423",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Ranking temporal data has not been studied until
                 recently, even though ranking is an important operator
                 (being promoted as a first-class citizen) in database
                 systems. However, only the instant top-$k$ queries on
                 temporal data were studied in, where objects with the
                 $k$ highest scores at a query time instance t are to be
                 retrieved. The instant top-$k$ definition clearly comes
                 with limitations (sensitive to outliers, difficult to
                 choose a meaningful query time $t$). A more flexible
                 and general ranking operation is to rank objects based
                 on the aggregation of their scores in a query interval,
                 which we dub the aggregate top-$k$ query on temporal
                 data. For example, return the top-10 weather stations
                 having the highest average temperature from 10/01/2010
                 to 10/07/2010; find the top-20 stocks having the
                 largest total transaction volumes from 02/05/2011 to
                 02/07/2011. This work presents a comprehensive study to
                 this problem by designing both exact and approximate
                 methods (with approximation quality guarantees). We
                 also provide theoretical analysis on the construction
                 cost, the index size, the update and the query costs of
                 each approach. Extensive experiments on large real
                 datasets clearly demonstrate the efficiency, the
                 effectiveness, and the scalability of our methods
                 compared to the baseline methods.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Funke:2012:CTD,
  author =       "Florian Funke and Alfons Kemper and Thomas Neumann",
  title =        "Compacting transactional data in hybrid {OLTP\&OLAP}
                 databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1424--1435",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Growing main memory sizes have facilitated database
                 management systems that keep the entire database in
                 main memory. The drastic performance improvements that
                 came along with these in-memory systems have made it
                 possible to reunite the two areas of online transaction
                 processing (OLTP) and online analytical processing
                 (OLAP): An emerging class of hybrid OLTP and OLAP
                 database systems allows to process analytical queries
                 directly on the transactional data. By offering
                 arbitrarily current snapshots of the transactional data
                 for OLAP, these systems enable real-time business
                 intelligence. Despite memory sizes of several Terabytes
                 in a single commodity server, RAM is still a precious
                 resource: Since free memory can be used for
                 intermediate results in query processing, the amount of
                 memory determines query performance to a large extent.
                 Consequently, we propose the compaction of
                 memory-resident databases. Compaction consists of two
                 tasks: First, separating the mutable working set from
                 the immutable ``frozen'' data. Second, compressing the
                 immutable data and optimizing it for efficient,
                 memory-consumption-friendly snapshotting. Our approach
                 reorganizes and compresses transactional data online
                 and yet hardly affects the mission-critical OLTP
                 throughput. This is achieved by unburdening the OLTP
                 threads from all additional processing and performing
                 these tasks asynchronously.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hall:2012:PTC,
  author =       "Alexander Hall and Olaf Bachmann and Robert B{\"u}ssow
                 and Silviu Ganceanu and Marc Nunkesser",
  title =        "Processing a trillion cells per mouse click",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1436--1446",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Column-oriented database systems have been a real game
                 changer for the industry in recent years. Highly tuned
                 and performant systems have evolved that provide users
                 with the possibility of answering ad hoc queries over
                 large datasets in an interactive manner. In this paper
                 we present the column-oriented datastore developed as
                 one of the central components of PowerDrill. It
                 combines the advantages of columnar data layout with
                 other known techniques (such as using composite range
                 partitions) and extensive algorithmic engineering on
                 key data structures. The main goal of the latter being
                 to reduce the main memory footprint and to increase the
                 efficiency in processing typical user queries. In this
                 combination we achieve large speed-ups. These enable a
                 highly interactive Web UI where it is common that a
                 single mouse click leads to processing a trillion
                 values in the underlying dataset.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Porobic:2012:OHI,
  author =       "Danica Porobic and Ippokratis Pandis and Miguel Branco
                 and Pinar T{\"o}z{\"u}n and Anastasia Ailamaki",
  title =        "{OLTP} on hardware islands",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1447--1458",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Modern hardware is abundantly parallel and
                 increasingly heterogeneous. The numerous processing
                 cores have nonuniform access latencies to the main
                 memory and to the processor caches, which causes
                 variability in the communication costs. Unfortunately,
                 database systems mostly assume that all processing
                 cores are the same and that microarchitecture
                 differences are not significant enough to appear in
                 critical database execution paths. As we demonstrate in
                 this paper, however, hardware heterogeneity does appear
                 in the critical path and conventional database
                 architectures achieve suboptimal and even worse,
                 unpredictable performance. We perform a detailed
                 performance analysis of OLTP deployments in servers
                 with multiple cores per CPU (multicore) and multiple
                 CPUs per server (multisocket). We compare different
                 database deployment strategies where we vary the number
                 and size of independent database instances running on a
                 single server, from a single shared-everything instance
                 to fine-grained shared-nothing configurations. We
                 quantify the impact of non-uniform hardware on various
                 deployments by (a) examining how efficiently each
                 deployment uses the available hardware resources and
                 (b) measuring the impact of distributed transactions
                 and skewed requests on different workloads. Finally, we
                 argue in favor of shared-nothing deployments that are
                 topology- and workload-aware and take advantage of fast
                 on-chip communication between islands of cores on the
                 same socket.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Patterson:2012:SSC,
  author =       "Stacy Patterson and Aaron J. Elmore and Faisal Nawab
                 and Divyakant Agrawal and Amr {El Abbadi}",
  title =        "Serializability, not serial: concurrency control and
                 availability in multi-datacenter datastores",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1459--1470",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We present a framework for concurrency control and
                 availability in multi-datacenter datastores. While we
                 consider Google's Megastore as our motivating example,
                 we define general abstractions for key components,
                 making our solution extensible to any system that
                 satisfies the abstraction properties. We first develop
                 and analyze a transaction management and replication
                 protocol based on a straightforward implementation of
                 the Paxos algorithm. Our investigation reveals that
                 this protocol acts as a concurrency prevention
                 mechanism rather than a concurrency control mechanism.
                 We then propose an enhanced protocol called Paxos with
                 Combination and Promotion (Paxos-CP) that provides true
                 transaction concurrency while requiring the same per
                 instance message complexity as the basic Paxos
                 protocol. Finally, we compare the performance of Paxos
                 and Paxos-CP in a multi-datacenter experimental study,
                 and we demonstrate that Paxos-CP results in
                 significantly fewer aborted transactions than basic
                 Paxos.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cheung:2012:APD,
  author =       "Alvin Cheung and Samuel Madden and Owen Arden and
                 Andrew C. Myers",
  title =        "Automatic partitioning of database applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1471--1482",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Database-backed applications are nearly ubiquitous in
                 our daily lives. Applications that make many small
                 accesses to the database create two challenges for
                 developers: increased latency and wasted resources from
                 numerous network round trips. A well-known technique to
                 improve transactional database application performance
                 is to convert part of the application into stored
                 procedures that are executed on the database server.
                 Unfortunately, this conversion is often difficult. In
                 this paper we describe Pyxis, a system that takes
                 database-backed applications and automatically
                 partitions their code into two pieces, one of which is
                 executed on the application server and the other on the
                 database server. Pyxis profiles the application and
                 server loads, statically analyzes the code's
                 dependencies, and produces a partitioning that
                 minimizes the number of control transfers as well as
                 the amount of data sent during each transfer. Our
                 experiments using TPC-C and TPC-W show that Pyxis is
                 able to generate partitions with up to 3x reduction in
                 latency and 1.7x improvement in throughput when
                 compared to a traditional non-partitioned
                 implementation and has comparable performance to that
                 of a custom stored procedure implementation.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2012:CCE,
  author =       "Jiannan Wang and Tim Kraska and Michael J. Franklin
                 and Jianhua Feng",
  title =        "{CrowdER}: crowdsourcing entity resolution",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1483--1494",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Entity resolution is central to data integration and
                 data cleaning. Algorithmic approaches have been
                 improving in quality, but remain far from perfect.
                 Crowdsourcing platforms offer a more accurate but
                 expensive (and slow) way to bring human insight into
                 the process. Previous work has proposed batching
                 verification tasks for presentation to human workers
                 but even with batching, a human-only approach is
                 infeasible for data sets of even moderate size, due to
                 the large numbers of matches to be tested. Instead, we
                 propose a hybrid human-machine approach in which
                 machines are used to do an initial, coarse pass over
                 all the data, and people are used to verify only the
                 most likely matching pairs. We show that for such a
                 hybrid system, generating the minimum number of
                 verification tasks of a given size is NP-Hard, but we
                 develop a novel two-tiered heuristic approach for
                 creating batched tasks. We describe this method, and
                 present the results of extensive experiments on real
                 data sets using a popular crowdsourcing platform. The
                 experiments show that our hybrid approach achieves both
                 good efficiency and high accuracy compared to
                 machine-only or human-only alternatives.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2012:WAJ,
  author =       "Caleb Chen Cao and Jieying She and Yongxin Tong and
                 Lei Chen",
  title =        "Whom to ask?: jury selection for decision making tasks
                 on micro-blog services",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1495--1506",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "It is universal to see people obtain knowledge on
                 micro-blog services by asking others decision making
                 questions. In this paper, we study the Jury Selection
                 Problem(JSP) by utilizing crowdsourcing for decision
                 making tasks on micro-blog services. Specifically, the
                 problem is to enroll a subset of crowd under a limited
                 budget, whose aggregated wisdom via Majority Voting
                 scheme has the lowest probability of drawing a wrong
                 answer(Jury Error Rate-JER). Due to various individual
                 error-rates of the crowd, the calculation of JER is
                 non-trivial. Firstly, we explicitly state that JER is
                 the probability when the number of wrong jurors is
                 larger than half of the size of a jury. To avoid the
                 exponentially increasing calculation of JER, we propose
                 two efficient algorithms and an effective bounding
                 technique. Furthermore, we study the Jury Selection
                 Problem on two crowdsourcing models, one is for
                 altruistic users(AltrM) and the other is for
                 incentive-requiring users(PayM) who require extra
                 payment when enrolled into a task. For the AltrM model,
                 we prove the monotonicity of JER on individual error
                 rate and propose an efficient exact algorithm for JSP.
                 For the PayM model, we prove the NP-hardness of JSP on
                 PayM and propose an efficient greedy-based heuristic
                 algorithm. Finally, we conduct a series of experiments
                 to investigate the traits of JSP, and validate the
                 efficiency and effectiveness of our proposed algorithms
                 on both synthetic and real micro-blog data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Yang:2012:AAL,
  author =       "Xiaochun Yang and Honglei Liu and Bin Wang",
  title =        "{ALAE}: accelerating local alignment with affine gap
                 exactly in biosequence databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1507--1518",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We study the problem of local alignment, which is
                 finding pairs of similar subsequences with gaps. The
                 problem exists in biosequence databases. BLAST is a
                 typical software for finding local alignment based on
                 heuristic, but could miss results. Using the
                 Smith-Waterman algorithm, we can find all local
                 alignments in $O(mn)$ time, where $m$ and $n$ are
                 lengths of a query and a text, respectively. A recent
                 exact approach BWT-SW improves the complexity of the
                 Smith-Waterman algorithm under constraints, but still
                 much slower than BLAST. This paper takes on the
                 challenge of designing an accurate and efficient
                 algorithm for evaluating local-alignment searches,
                 especially for long queries. In this paper, we propose
                 an efficient software called ALAE to speed up BWT-SW
                 using a compressed suffix array. ALAE utilizes a family
                 of filtering techniques to prune meaningless
                 calculations and an algorithm for reusing score
                 calculations. We also give a mathematical analysis and
                 show that the upper bound of the total number of
                 calculated entries using ALAE could vary from 4.50
                 mn$^{0.520}$ to 9.05 mn$^{0.896}$ for random DNA
                 sequences and vary from 8.28 mn$^{0.364}$ to 7.49
                 mn$^{0.723}$ for random protein sequences. We
                 demonstrate the significant performance improvement of
                 ALAE on BWT-SW using a thorough experimental study on
                 real biosequences. ALAE guarantees correctness and
                 accelerates BLAST for most of parameters.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Candan:2012:SCD,
  author =       "K. Sel{\c{c}}uk Candan and Rosaria Rossini and Xiaolan
                 Wang and Maria Luisa Sapino",
  title =        "{sDTW}: computing {DTW} distances using locally
                 relevant constraints based on salient feature
                 alignments",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1519--1530",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Many applications generate and consume temporal data
                 and retrieval of time series is a key processing step
                 in many application domains. Dynamic time warping (DTW)
                 distance between time series of size N and M is
                 computed relying on a dynamic programming approach
                 which creates and fills an N x M grid to search for an
                 optimal warp path. Since this can be costly, various
                 heuristics have been proposed to cut away the
                 potentially unproductive portions of the DTW grid. In
                 this paper, we argue that time series often carry
                 structural features that can be used for identifying
                 locally relevant constraints to eliminate redundant
                 work. Relying on this observation, we propose salient
                 feature based sDTW algorithms which first identify
                 robust salient features in the given time series and
                 then find a consistent alignment of these to establish
                 the boundaries for the warp path search. More
                 specifically, we propose alternative fixed
                 core\&adaptive width, adaptive core\&fixed width, and
                 adaptive core\&adaptive width strategies which enforce
                 different constraints reflecting the high level
                 structural characteristics of the series in the data
                 set. Experiment results show that the proposed sDTW
                 algorithms help achieve much higher accuracy in DTW
                 computation and time series retrieval than fixed core
                 \& fixed width algorithms that do not leverage local
                 features of the given time series.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tauheed:2012:SPL,
  author =       "Farhan Tauheed and Thomas Heinis and Felix
                 Sch{\"u}rmann and Henry Markram and Anastasia
                 Ailamaki",
  title =        "{SCOUT}: prefetching for latent structure following
                 queries",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1531--1542",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Today's scientists are quickly moving from in vitro to
                 in silico experimentation: they no longer analyze
                 natural phenomena in a petri dish, but instead they
                 build models and simulate them. Managing and analyzing
                 the massive amounts of data involved in simulations is
                 a major task. Yet, they lack the tools to efficiently
                 work with data of this size. One problem many
                 scientists share is the analysis of the massive spatial
                 models they build. For several types of analysis they
                 need to interactively follow the structures in the
                 spatial model, e.g., the arterial tree, neuron fibers,
                 etc., and issue range queries along the way. Each query
                 takes long to execute, and the total time for executing
                 a sequence of queries significantly delays data
                 analysis. Prefetching the spatial data reduces the
                 response time considerably, but known approaches do not
                 prefetch with high accuracy. We develop SCOUT, a
                 structure-aware method for prefetching data along
                 interactive spatial query sequences. SCOUT uses an
                 approximate graph model of the structures involved in
                 past queries and attempts to identify what particular
                 structure the user follows. Our experiments with
                 neuro-science data show that SCOUT prefetches with an
                 accuracy from 71\% to 92\%, which translates to a
                 speedup of 4x-15x. SCOUT also improves the prefetching
                 accuracy on datasets from other scientific domains,
                 such as medicine and biology.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wang:2012:API,
  author =       "Kaibo Wang and Yin Huai and Rubao Lee and Fusheng Wang
                 and Xiaodong Zhang and Joel H. Saltz",
  title =        "Accelerating pathology image data cross-comparison on
                 {CPU--GPU} hybrid systems",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1543--1554",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As an important application of spatial databases in
                 pathology imaging analysis, cross-comparing the spatial
                 boundaries of a huge amount of segmented micro-anatomic
                 objects demands extremely data- and compute-intensive
                 operations, requiring high throughput at an affordable
                 cost. However, the performance of spatial database
                 systems has not been satisfactory since their
                 implementations of spatial operations cannot fully
                 utilize the power of modern parallel hardware. In this
                 paper, we provide a customized software solution that
                 exploits GPUs and multi-core CPUs to accelerate spatial
                 cross-comparison in a cost-effective way. Our solution
                 consists of an efficient GPU algorithm and a pipelined
                 system framework with task migration support. Extensive
                 experiments with real-world data sets demonstrate the
                 effectiveness of our solution, which improves the
                 performance of spatial cross-comparison by over 18
                 times compared with a parallelized spatial database
                 approach.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2012:RER,
  author =       "Jiexing Li and Arnd Christian K{\"o}nig and Vivek
                 Narasayya and Surajit Chaudhuri",
  title =        "Robust estimation of resource consumption for {SQL}
                 queries using statistical techniques",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1555--1566",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The ability to estimate resource consumption of SQL
                 queries is crucial for a number of tasks in a database
                 system such as admission control, query scheduling and
                 costing during query optimization. Recent work has
                 explored the use of statistical techniques for resource
                 estimation in place of the manually constructed cost
                 models used in query optimization. Such techniques,
                 which require as training data examples of resource
                 usage in queries, offer the promise of superior
                 estimation accuracy since they can account for factors
                 such as hardware characteristics of the system or bias
                 in cardinality estimates. However, the proposed
                 approaches lack robustness in that they do not
                 generalize well to queries that are different from the
                 training examples, resulting in significant estimation
                 errors. Our approach aims to address this problem by
                 combining knowledge of database query processing with
                 statistical models. We model resource-usage at the
                 level of individual operators, with different models
                 and features for each operator type, and explicitly
                 model the asymptotic behavior of each operator. This
                 results in significantly better estimation accuracy and
                 the ability to estimate resource usage of arbitrary
                 plans, even when they are very different from the
                 training instances. We validate our approach using
                 various large scale real-life and benchmark workloads
                 on Microsoft SQL Server.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Das:2012:WTW,
  author =       "Mahashweta Das and Saravanan Thirumuruganathan and
                 Sihem Amer-Yahia and Gautam Das and Cong Yu",
  title =        "Who tags what?: an analysis framework",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1567--1578",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The rise of Web 2.0 is signaled by sites such as
                 Flickr, del.icio.us, and YouTube, and social tagging is
                 essential to their success. A typical tagging action
                 involves three components, user, item (e.g., photos in
                 Flickr), and tags (i.e., words or phrases). Analyzing
                 how tags are assigned by certain users to certain items
                 has important implications in helping users search for
                 desired information. In this paper, we explore common
                 analysis tasks and propose a dual mining framework for
                 social tagging behavior mining. This framework is
                 centered around two opposing measures, similarity and
                 diversity, being applied to one or more tagging
                 components, and therefore enables a wide range of
                 analysis scenarios such as characterizing similar users
                 tagging diverse items with similar tags, or diverse
                 users tagging similar items with diverse tags, etc. By
                 adopting different concrete measures for similarity and
                 diversity in the framework, we show that a wide range
                 of concrete analysis problems can be defined and they
                 are NP-Complete in general. We design efficient
                 algorithms for solving many of those problems and
                 demonstrate, through comprehensive experiments over
                 real data, that our algorithms significantly
                 out-perform the exact brute-force approach without
                 compromising analysis result quality.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Zhu:2012:GFE,
  author =       "Haohan Zhu and George Kollios and Vassilis Athitsos",
  title =        "A generic framework for efficient and effective
                 subsequence retrieval",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1579--1590",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper proposes a general framework for matching
                 similar subsequences in both time series and string
                 databases. The matching results are pairs of query
                 subsequences and database subsequences. The framework
                 finds all possible pairs of similar subsequences if the
                 distance measure satisfies the ``consistency''
                 property, which is a property introduced in this paper.
                 We show that most popular distance functions, such as
                 the Euclidean distance, DTW, ERP, the Frech{\'e}t
                 distance for time series, and the Hamming distance and
                 Levenshtein distance for strings, are all
                 ``consistent''. We also propose a generic index
                 structure for metric spaces named ``reference net''.
                 The reference net occupies $O(n)$ space, where $n$ is
                 the size of the dataset and is optimized to work well
                 with our framework. The experiments demonstrate the
                 ability of our method to improve retrieval performance
                 when combined with diverse distance measures. The
                 experiments also illustrate that the reference net
                 scales well in terms of space overhead and query
                 time.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dittrich:2012:OAE,
  author =       "Jens Dittrich and Jorge-Arnulfo Quian{\'e}-Ruiz and
                 Stefan Richter and Stefan Schuh and Alekh Jindal and
                 J{\"o}rg Schad",
  title =        "Only aggressive elephants are fast elephants",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1591--1602",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Yellow elephants are slow. A major reason is that they
                 consume their inputs entirely before responding to an
                 elephant rider's orders. Some clever riders have
                 trained their yellow elephants to only consume parts of
                 the inputs before responding. However, the teaching
                 time to make an elephant do that is high. So high that
                 the teaching lessons often do not pay off. We take a
                 different approach. We make elephants aggressive; only
                 this will make them very fast. We propose HAIL (Hadoop
                 Aggressive Indexing Library), an enhancement of HDFS
                 and Hadoop MapReduce that dramatically improves
                 runtimes of several classes of MapReduce jobs. HAIL
                 changes the upload pipeline of HDFS in order to create
                 different clustered indexes on each data block replica.
                 An interesting feature of HAIL is that we typically
                 create a win-win situation: we improve both data upload
                 to HDFS and the runtime of the actual Hadoop MapReduce
                 job. In terms of data upload, HAIL improves over HDFS
                 by up to 60\% with the default replication factor of
                 three. In terms of query execution, we demonstrate that
                 HAIL runs up to 68x faster than Hadoop. In our
                 experiments, we use six clusters including physical and
                 EC2 clusters of up to 100 nodes. A series of
                 scalability experiments also demonstrates the
                 superiority of HAIL.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Li:2012:MLP,
  author =       "Rui Li and Shengjie Wang and Kevin Chen-Chuan Chang",
  title =        "Multiple location profiling for users and
                 relationships from social network and content",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1603--1614",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Users' locations are important for many applications
                 such as personalized search and localized content
                 delivery. In this paper, we study the problem of
                 profiling Twitter users' locations with their following
                 network and tweets. We propose a multiple location
                 profiling model (MLP), which has three key features:
                 (1) it formally models how likely a user follows
                 another user given their locations and how likely a
                 user tweets a venue given his location, (2) it
                 fundamentally captures that a user has multiple
                 locations and his following relationships and tweeted
                 venues can be related to any of his locations, and some
                 of them are even noisy, and (3) it novelly utilizes the
                 home locations of some users as partial supervision. As
                 a result, MLP not only discovers users' locations
                 accurately and completely, but also ``explains'' each
                 following relationship by revealing users' true
                 locations in the relationship. Experiments on a
                 large-scale data set demonstrate those advantages.
                 Particularly, (1) for predicting users' home locations,
                 MLP successfully places 62\% users and out-performs two
                 state-of-the-art methods by 10\% in accuracy, (2) for
                 discovering users' multiple locations, MLP improves the
                 baseline methods by 14\% in recall, and (3) for
                 explaining following relationships, MLP achieves 57\%
                 accuracy.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kang:2012:FBE,
  author =       "Woon-Hak Kang and Sang-Won Lee and Bongki Moon",
  title =        "Flash-based extended cache for higher throughput and
                 faster recovery",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1615--1626",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Considering the current price gap between disk and
                 flash memory drives, for applications dealing with
                 large scale data, it will be economically more sensible
                 to use flash memory drives to supplement disk drives
                 rather than to replace them. This paper presents FaCE,
                 which is a new low-overhead caching strategy that uses
                 flash memory as an extension to the DRAM buffer. FaCE
                 aims at improving the transaction throughput as well as
                 shortening the recovery time from a system failure. To
                 achieve the goals, we propose two novel algorithms for
                 flash cache management, namely, Multi-Version FIFO
                 replacement and Group Second Chance. One striking
                 result from FaCE is that using a small flash memory
                 drive as a caching device could deliver even higher
                 throughput than using a large flash memory drive to
                 store the entire database tables. This was possible due
                 to flash write optimization as well as disk access
                 reduction obtained by the FaCE caching methods. In
                 addition, FaCE takes advantage of the non-volatility of
                 flash memory to fully support database recovery by
                 extending the scope of a persistent database to include
                 the data pages stored in the flash cache. We have
                 implemented FaCE in the PostgreSQL open source database
                 server and demonstrated its effectiveness for TPC-C
                 benchmarks.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Bender:2012:DTH,
  author =       "Michael A. Bender and Martin Farach-Colton and Rob
                 Johnson and Russell Kraner and Bradley C. Kuszmaul and
                 Dzejla Medjedovic and Pablo Montes and Pradeep Shetty
                 and Richard P. Spillane and Erez Zadok",
  title =        "Don't thrash: how to cache your hash on flash",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1627--1637",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper presents new alternatives to the well-known
                 Bloom filter data structure. The Bloom filter, a
                 compact data structure supporting set insertion and
                 membership queries, has found wide application in
                 databases, storage systems, and networks. Because the
                 Bloom filter performs frequent random reads and writes,
                 it is used almost exclusively in RAM, limiting the size
                 of the sets it can represent. This paper first
                 describes the quotient filter, which supports the basic
                 operations of the Bloom filter, achieving roughly
                 comparable performance in terms of space and time, but
                 with better data locality. Operations on the quotient
                 filter require only a small number of contiguous
                 accesses. The quotient filter has other advantages over
                 the Bloom filter: it supports deletions, it can be
                 dynamically resized, and two quotient filters can be
                 efficiently merged. The paper then gives two data
                 structures, the buffered quotient filter and the
                 cascade filter, which exploit the quotient filter
                 advantages and thus serve as SSD-optimized alternatives
                 to the Bloom filter. The cascade filter has better
                 asymptotic I/O performance than the buffered quotient
                 filter, but the buffered quotient filter outperforms
                 the cascade filter on small to medium data sets. Both
                 data structures significantly outperform
                 recently-proposed SSD-optimized Bloom filter variants,
                 such as the elevator Bloom filter, buffered Bloom
                 filter, and forest-structured Bloom filter. In
                 experiments, the cascade filter and buffered quotient
                 filter performed insertions 8.6--11 times faster than
                 the fastest Bloom filter variant and performed lookups
                 0.94--2.56 times faster.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Isele:2012:LEL,
  author =       "Robert Isele and Christian Bizer",
  title =        "Learning expressive linkage rules using genetic
                 programming",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1638--1649",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "A central problem in data integration and data
                 cleansing is to find entities in different data sources
                 that describe the same real-world object. Many existing
                 methods for identifying such entities rely on explicit
                 linkage rules which specify the conditions that
                 entities must fulfill in order to be considered to
                 describe the same real-world object. In this paper, we
                 present the GenLink algorithm for learning expressive
                 linkage rules from a set of existing reference links
                 using genetic programming. The algorithm is capable of
                 generating linkage rules which select discriminative
                 properties for comparison, apply chains of data
                 transformations to normalize property values, choose
                 appropriate distance measures and thresholds and
                 combine the results of multiple comparisons using
                 non-linear aggregation functions. Our experiments show
                 that the GenLink algorithm outperforms the
                 state-of-the-art genetic programming approach to
                 learning linkage rules recently presented by Carvalho
                 et. al. and is capable of learning linkage rules which
                 achieve a similar accuracy as human written rules for
                 the same problem.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Tong:2012:MFI,
  author =       "Yongxin Tong and Lei Chen and Yurong Cheng and Philip
                 S. Yu",
  title =        "Mining frequent itemsets over uncertain databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1650--1661",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In recent years, due to the wide applications of
                 uncertain data, mining frequent itemsets over uncertain
                 databases has attracted much attention. In uncertain
                 databases, the support of an itemset is a random
                 variable instead of a fixed occurrence counting of this
                 itemset. Thus, unlike the corresponding problem in
                 deterministic databases where the frequent itemset has
                 a unique definition, the frequent itemset under
                 uncertain environments has two different definitions so
                 far. The first definition, referred as the expected
                 support-based frequent itemset, employs the expectation
                 of the support of an itemset to measure whether this
                 itemset is frequent. The second definition, referred as
                 the probabilistic frequent itemset, uses the
                 probability of the support of an itemset to measure its
                 frequency. Thus, existing work on mining frequent
                 itemsets over uncertain databases is divided into two
                 different groups and no study is conducted to
                 comprehensively compare the two different definitions.
                 In addition, since no uniform experimental platform
                 exists, current solutions for the same definition even
                 generate inconsistent results. In this paper, we
                 firstly aim to clarify the relationship between the two
                 different definitions. Through extensive experiments,
                 we verify that the two definitions have a tight
                 connection and can be unified together when the size of
                 data is large enough. Secondly, we provide baseline
                 implementations of eight existing representative
                 algorithms and test their performances with uniform
                 measures fairly. Finally, according to the fair tests
                 over many different benchmark data sets, we clarify
                 several existing inconsistent conclusions and discuss
                 some new findings.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dallachiesa:2012:UTS,
  author =       "Michele Dallachiesa and Besmira Nushi and Katsiaryna
                 Mirylenka and Themis Palpanas",
  title =        "Uncertain time-series similarity: return to the
                 basics",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1662--1673",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In the last years there has been a considerable
                 increase in the availability of continuous sensor
                 measurements in a wide range of application domains,
                 such as Location-Based Services (LBS), medical
                 monitoring systems, manufacturing plants and
                 engineering facilities to ensure efficiency, product
                 quality and safety, hydrologic and geologic observing
                 systems, pollution management, and others. Due to the
                 inherent imprecision of sensor observations, many
                 investigations have recently turned into querying,
                 mining and storing uncertain data. Uncertainty can also
                 be due to data aggregation, privacy-preserving
                 transforms, and error-prone mining algorithms. In this
                 study, we survey the techniques that have been proposed
                 specifically for modeling and processing uncertain time
                 series, an important model for temporal data. We
                 provide an analytical evaluation of the alternatives
                 that have been proposed in the literature, highlighting
                 the advantages and disadvantages of each approach, and
                 further compare these alternatives with two additional
                 techniques that were carefully studied before. We
                 conduct an extensive experimental evaluation with 17
                 real datasets, and discuss some surprising results,
                 which suggest that a fruitful research direction is to
                 take into account the temporal correlations in the time
                 series. Based on our evaluations, we also provide
                 guidelines useful for the practitioners in the field.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dasu:2012:SDC,
  author =       "Tamraparni Dasu and Ji Meng Loh",
  title =        "Statistical distortion: consequences of data
                 cleaning",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1674--1683",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We introduce the notion of statistical distortion as
                 an essential metric for measuring the effectiveness of
                 data cleaning strategies. We use this metric to propose
                 a widely applicable yet scalable experimental framework
                 for evaluating data cleaning strategies along three
                 dimensions: glitch improvement, statistical distortion
                 and cost-related criteria. Existing metrics focus on
                 glitch improvement and cost, but not on the statistical
                 impact of data cleaning strategies. We illustrate our
                 framework on real world data, with a comprehensive
                 suite of experiments and analyses.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lang:2012:TEE,
  author =       "Willis Lang and Stavros Harizopoulos and Jignesh M.
                 Patel and Mehul A. Shah and Dimitris Tsirogiannis",
  title =        "Towards energy-efficient database cluster design",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "11",
  pages =        "1684--1695",
  month =        jul,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:15 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Energy is a growing component of the operational cost
                 for many ``big data'' deployments, and hence has become
                 increasingly important for practitioners of large-scale
                 data analysis who require scale-out clusters or
                 parallel DBMS appliances. Although a number of recent
                 studies have investigated the energy efficiency of
                 DBMSs, none of these studies have looked at the
                 architectural design space of energy-efficient parallel
                 DBMS clusters. There are many challenges to increasing
                 the energy efficiency of a DBMS cluster, including
                 dealing with the inherent scaling inefficiency of
                 parallel data processing, and choosing the appropriate
                 energy-efficient hardware. In this paper, we
                 experimentally examine and analyze a number of key
                 parameters related to these challenges for designing
                 energy-efficient database clusters. We explore the
                 cluster design space using empirical results and
                 propose a model that considers the key bottlenecks to
                 energy efficiency in a parallel DBMS. This paper
                 represents a key first step in designing
                 energy-efficient database clusters, which is
                 increasingly important given the trend toward parallel
                 database appliances.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jensen:2012:DMS,
  author =       "Christian S. Jensen",
  title =        "Data management on the spatial web",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1696--1696",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Due in part to the increasing mobile use of the web
                 and the proliferation of geo-positioning, the web is
                 fast acquiring a significant spatial aspect. Content
                 and users are being augmented with locations that are
                 used increasingly by location-based services. Studies
                 suggest that each week, several billion web queries are
                 issued that have local intent and target spatial web
                 objects. These are points of interest with a web
                 presence, and they thus have locations as well as
                 textual descriptions. This development has given
                 prominence to spatial web data management, an area ripe
                 with new and exciting opportunities and challenges. The
                 research community has embarked on inventing and
                 supporting new query functionality for the spatial web.
                 Different kinds of spatial web queries return objects
                 that are near a location argument and are relevant to a
                 text argument. To support such queries, it is important
                 to be able to rank objects according to their relevance
                 to a query. And it is important to be able to process
                 the queries with low latency. The talk offers an
                 overview of key aspects of the spatial web. Based on
                 recent results obtained by the speaker and his
                 colleagues, the talk explores new query functionality
                 enabled by the setting. Further, the talk offers
                 insight into the data management techniques capable of
                 supporting such functionality.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Dietrich:2012:DAO,
  author =       "Brenda Dietrich",
  title =        "Data analytics opportunities in a smarter planet",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1697--1697",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "New applications of computing are being enabled by
                 instrumentation of physical entities, aggregation of
                 data, and the analysis of the data. The resulting
                 integration of information and control permits
                 efficient and effective management of complex man-made
                 systems. Examples include transportation systems,
                 buildings, electrical grids, health care systems,
                 governments, and supply chains. Achieving this vision
                 requires extensive data integration and analysis, over
                 diverse, rapidly changing, and often uncertain data.
                 There are many challenges, requiring both new data
                 management techniques as well as new mathematics,
                 forcing new collaborations as the basis of the new
                 ``Data Science''. Needs and opportunities will be
                 discussed in the context of specific pilots and
                 projects.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Sahin:2012:CEM,
  author =       "Kenan Sahin",
  title =        "Challenges in economic massive content storage and
                 management ({MCSAM}) in the era of self-organizing,
                 self-expanding and self-linking data clusters",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1698--1698",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Rapid spread of social networks, global on-line
                 shopping, post 9/11 security oriented linking of data
                 bases and foremost the global adoption of smart
                 phones/devices, among other phenomena, are transforming
                 data clusters into dynamic and almost uncontrollable
                 entities that have their own local intelligence,
                 clients and objectives. The scale and rapidity of
                 change is such that large scale innovations in content
                 storage and management are urgently needed if the
                 diseconomies of scale and complexity are to be
                 mitigated. The field needs to reinvent itself.
                 Istanbul, a city that has reinvented itself many times
                 is an excellent venue to engage in such a discussion
                 and for me to offer suggestions and proposals that
                 derive from personal experiences that span academia,
                 start ups, R\&D firms and Bell Labs as well my early
                 years spent in Istanbul.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Manku:2012:AFC,
  author =       "Gurmeet Singh Manku and Rajeev Motwani",
  title =        "Approximate frequency counts over data streams",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1699--1699",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Research in data stream algorithms has blossomed since
                 late 90s. The talk will trace the history of the
                 Approximate Frequency Counts paper, how it was
                 conceptualized and how it influenced data stream
                 research. The talk will also touch upon a recent
                 development: analysis of personal data streams for
                 improving our quality of lives.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Hellerstein:2012:MAL,
  author =       "Joseph M. Hellerstein and Christoper R{\'e} and
                 Florian Schoppmann and Daisy Zhe Wang and Eugene
                 Fratkin and Aleksander Gorajek and Kee Siong Ng and
                 Caleb Welton and Xixuan Feng and Kun Li and Arun
                 Kumar",
  title =        "The {MADlib} analytics library: or {MAD} skills, the
                 {SQL}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1700--1711",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "MADlib is a free, open-source library of in-database
                 analytic methods. It provides an evolving suite of
                 SQL-based algorithms for machine learning, data mining
                 and statistics that run at scale within a database
                 engine, with no need for data import/export to other
                 tools. The goal is for MADlib to eventually serve a
                 role for scalable database systems that is similar to
                 the CRAN library for R: a community repository of
                 statistical methods, this time written with scale and
                 parallelism in mind. In this paper we introduce the
                 MADlib project, including the background that led to
                 its beginnings, and the motivation for its open-source
                 nature. We provide an overview of the library's
                 architecture and design patterns, and provide a
                 description of various statistical methods in that
                 context. We include performance and speedup results of
                 a core design pattern from one of those methods over
                 the Greenplum parallel DBMS on a modest-sized test
                 cluster. We then report on two initial efforts at
                 incorporating academic research into MADlib, which is
                 one of the project's goals. MADlib is freely available
                 at http://madlib.net, and the project is open for
                 contributions of both new methods, and ports to
                 additional database platforms.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Floratou:2012:CEH,
  author =       "Avrilia Floratou and Nikhil Teletia and David J.
                 DeWitt and Jignesh M. Patel and Donghui Zhang",
  title =        "Can the elephants handle the {NoSQL} onslaught?",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1712--1723",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this new era of ``big data'', traditional DBMSs are
                 under attack from two sides. At one end of the
                 spectrum, the use of document store NoSQL systems (e.g.
                 MongoDB) threatens to move modern Web 2.0 applications
                 away from traditional RDBMSs. At the other end of the
                 spectrum, big data DSS analytics that used to be the
                 domain of parallel RDBMSs is now under attack by
                 another class of NoSQL data analytics systems, such as
                 Hive on Hadoop. So, are the traditional RDBMSs, aka
                 ``big elephants'', doomed as they are challenged from
                 both ends of this ``big data'' spectrum? In this paper,
                 we compare one representative NoSQL system from each
                 end of this spectrum with SQL Server, and analyze the
                 performance and scalability aspects of each of these
                 approaches (NoSQL vs. SQL) on two workloads (decision
                 support analysis and interactive data-serving) that
                 represent the two ends of the application spectrum. We
                 present insights from this evaluation and speculate on
                 potential trends for the future.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rabl:2012:SBD,
  author =       "Tilmann Rabl and Sergio G{\'o}mez-Villamor and
                 Mohammad Sadoghi and Victor Munt{\'e}s-Mulero and
                 Hans-Arno Jacobsen and Serge Mankovskii",
  title =        "Solving big data challenges for enterprise application
                 performance management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1724--1735",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As the complexity of enterprise systems increases, the
                 need for monitoring and analyzing such systems also
                 grows. A number of companies have built sophisticated
                 monitoring tools that go far beyond simple resource
                 utilization reports. For example, based on
                 instrumentation and specialized APIs, it is now
                 possible to monitor single method invocations and trace
                 individual transactions across geographically
                 distributed systems. This high-level of detail enables
                 more precise forms of analysis and prediction but comes
                 at the price of high data rates (i.e., big data). To
                 maximize the benefit of data monitoring, the data has
                 to be stored for an extended period of time for
                 ulterior analysis. This new wave of big data analytics
                 imposes new challenges especially for the application
                 performance monitoring systems. The monitoring data has
                 to be stored in a system that can sustain the high data
                 rates and at the same time enable an up-to-date view of
                 the underlying infrastructure. With the advent of
                 modern key-value stores, a variety of data storage
                 systems have emerged that are built with a focus on
                 scalability and high data rates as predominant in this
                 monitoring use case. In this work, we present our
                 experience and a comprehensive performance evaluation
                 of six modern (open-source) data stores in the context
                 of application performance monitoring as part of CA
                 Technologies initiative. We evaluated these systems
                 with data and workloads that can be found in
                 application performance monitoring, as well as, on-line
                 advertisement, power monitoring, and many other use
                 cases. We present our insights not only as performance
                 results but also as lessons learned and our experience
                 relating to the setup and configuration complexity of
                 these data stores in an industry setting.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Shinnar:2012:MIP,
  author =       "Avraham Shinnar and David Cunningham and Vijay
                 Saraswat and Benjamin Herta",
  title =        "{M3R}: increased performance for in-memory {Hadoop}
                 jobs",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1736--1747",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Main Memory Map Reduce (M3R) is a new implementation
                 of the Hadoop Map Reduce (HMR) API targeted at online
                 analytics on high mean-time-to-failure clusters. It
                 does not support resilience, and supports only those
                 workloads which can fit into cluster memory. In return,
                 it can run HMR jobs unchanged --- including jobs
                 produced by compilers for higher-level languages such
                 as Pig, Jaql, and SystemML and interactive front-ends
                 like IBM BigSheets --- while providing significantly
                 better performance than the Hadoop engine on several
                 workloads (e.g. 45x on some input sizes for sparse
                 matrix vector multiply). M3R also supports extensions
                 to the HMR API which can enable Map Reduce jobs to run
                 faster on the M3R engine, while not affecting their
                 performance under the Hadoop engine.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Rosch:2012:SAH,
  author =       "Philipp R{\"o}sch and Lars Dannecker and Franz
                 F{\"a}rber and Gregor Hackenbroich",
  title =        "A storage advisor for hybrid-store databases",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1748--1758",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "With the SAP HANA database, SAP offers a
                 high-performance in-memory hybrid-store database.
                 Hybrid-store databases---that is, databases supporting
                 row- and column-oriented data management---are getting
                 more and more prominent. While the columnar management
                 offers high-performance capabilities for analyzing
                 large quantities of data, the row-oriented store can
                 handle transactional point queries as well as inserts
                 and updates more efficiently. To effectively take
                 advantage of both stores at the same time the novel
                 question whether to store the given data row- or
                 column-oriented arises. We tackle this problem with a
                 storage advisor tool that supports database
                 administrators at this decision. Our proposed storage
                 advisor recommends the optimal store based on data and
                 query characteristics; its core is a cost model to
                 estimate and compare query execution times for the
                 different stores. Besides a per-table decision, our
                 tool also considers to horizontally and vertically
                 partition the data and manage the partitions on
                 different stores. We evaluated the storage advisor for
                 the use in the SAP HANA database; we show the
                 recommendation quality as well as the benefit of having
                 the data in the optimal store with respect to increased
                 query performance.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Switakowski:2012:CSP,
  author =       "Michal 'Switakowski and Peter Boncz and Marcin
                 Zukowski",
  title =        "From cooperative scans to predictive buffer
                 management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1759--1770",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In analytical applications, database systems often
                 need to sustain workloads with multiple concurrent
                 scans hitting the same table. The Cooperative Scans
                 (CScans) framework, which introduces an Active Buffer
                 Manager (ABM) component into the database architecture,
                 has been the most effective and elaborate response to
                 this problem, and was initially developed in the X100
                 research prototype. We now report on the experiences of
                 integrating Cooperative Scans into its
                 industrial-strength successor, the Vectorwise database
                 product. During this implementation we invented a
                 simpler optimization of concurrent scan buffer
                 management, called Predictive Buffer Management (PBM).
                 PBM is based on the observation that in a workload with
                 long-running scans, the buffer manager has quite a bit
                 of information on the workload in the immediate future,
                 such that an approximation of the ideal OPT algorithm
                 becomes feasible. In the evaluation on both synthetic
                 benchmarks as well as a TPC-H throughput run we compare
                 the benefits of naive buffer management (LRU) versus
                 CScans, PBM and OPT; showing that PBM achieves benefits
                 close to Cooperative Scans, while incurring much lower
                 architectural impact.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lee:2012:ULI,
  author =       "George Lee and Jimmy Lin and Chuang Liu and Andrew
                 Lorek and Dmitriy Ryaboy",
  title =        "The unified logging infrastructure for data analytics
                 at {Twitter}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1771--1780",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In recent years, there has been a substantial amount
                 of work on large-scale data analytics using
                 Hadoop-based platforms running on large clusters of
                 commodity machines. A less-explored topic is how those
                 data, dominated by application logs, are collected and
                 structured to begin with. In this paper, we present
                 Twitter's production logging infrastructure and its
                 evolution from application-specific logging to a
                 unified ``client events'' log format, where messages
                 are captured in common, well-formatted, flexible Thrift
                 messages. Since most analytics tasks consider the user
                 session as the basic unit of analysis, we
                 pre-materialize ``session sequences'', which are
                 compact summaries that can answer a large class of
                 common queries quickly. The development of this
                 infrastructure has streamlined log collection and data
                 analysis, thereby improving our ability to rapidly
                 experiment and iterate on various aspects of the
                 service.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Talius:2012:TLB,
  author =       "Tomas Talius and Robin Dhamankar and Andrei Dumitrache
                 and Hanuma Kodavalla",
  title =        "Transaction log based application error recovery and
                 point in-time query",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1781--1789",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Database backups have traditionally been used as the
                 primary mechanism to recover from hardware and user
                 errors. High availability solutions maintain redundant
                 copies of data that can be used to recover from most
                 failures except user or application errors. Database
                 backups are neither space nor time efficient for
                 recovering from user errors which typically occur in
                 the recent past and affect a small portion of the
                 database. Moreover periodic full backups impact user
                 workload and increase storage costs. In this paper we
                 present a scheme that can be used for both user and
                 application error recovery starting from the current
                 state and rewinding the database back in time using the
                 transaction log. While we provide a consistent view of
                 the entire database as of a point in time in the past,
                 the actual prior versions are produced only for data
                 that is accessed. We make the as of data accessible to
                 arbitrary point in time queries by integrating with the
                 database snapshot feature in Microsoft SQL Server.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lamb:2012:VAD,
  author =       "Andrew Lamb and Matt Fuller and Ramakrishna
                 Varadarajan and Nga Tran and Ben Vandiver and Lyric
                 Doshi and Chuck Bear",
  title =        "The {Vertica Analytic Database}: {C-Store} 7 years
                 later",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1790--1801",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper describes the system architecture of the
                 Vertica Analytic Database (Vertica), a
                 commercialization of the design of the C-Store research
                 prototype. Vertica demonstrates a modern commercial
                 RDBMS system that presents a classical relational
                 interface while at the same time achieving the high
                 performance expected from modern ``web scale'' analytic
                 systems by making appropriate architectural choices.
                 Vertica is also an instructive lesson in how academic
                 systems research can be directly commercialized into a
                 successful product.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Chen:2012:IAP,
  author =       "Yanpei Chen and Sara Alspaugh and Randy Katz",
  title =        "Interactive analytical processing in big data systems:
                 a cross-industry study of {MapReduce} workloads",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1802--1813",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Within the past few years, organizations in diverse
                 industries have adopted MapReduce-based systems for
                 large-scale data processing. Along with these new
                 users, important new workloads have emerged which
                 feature many small, short, and increasingly interactive
                 jobs in addition to the large, long-running batch jobs
                 for which MapReduce was originally designed. As
                 interactive, large-scale query processing is a strength
                 of the RDBMS community, it is important that lessons
                 from that field be carried over and applied where
                 possible in this new domain. However, these new
                 workloads have not yet been described in the
                 literature. We fill this gap with an empirical analysis
                 of MapReduce traces from six separate business-critical
                 deployments inside Facebook and at Cloudera customers
                 in e-commerce, telecommunications, media, and retail.
                 Our key contribution is a characterization of new
                 MapReduce workloads which are driven in part by
                 interactive analysis, and which make heavy use of
                 query-like programming frameworks on top of MapReduce.
                 These workloads display diverse behaviors which
                 invalidate prior assumptions about MapReduce such as
                 uniform data access, regular diurnal patterns, and
                 prevalence of large jobs. A secondary contribution is a
                 first step towards creating a TPC-like data processing
                 benchmark for MapReduce.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Lam:2012:MMS,
  author =       "Wang Lam and Lu Liu and Sts Prasad and Anand Rajaraman
                 and Zoheb Vacheri and AnHai Doan",
  title =        "{Muppet}: {MapReduce}-style processing of fast data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1814--1825",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "MapReduce has emerged as a popular method to process
                 big data. In the past few years, however, not just big
                 data, but fast data has also exploded in volume and
                 availability. Examples of such data include sensor data
                 streams, the Twitter Firehose, and Facebook updates.
                 Numerous applications must process fast data. Can we
                 provide a MapReduce-style framework so that developers
                 can quickly write such applications and execute them
                 over a cluster of machines, to achieve low latency and
                 high scalability? In this paper we report on our
                 investigation of this question, as carried out at
                 Kosmix and WalmartLabs. We describe MapUpdate, a
                 framework like MapReduce, but specifically developed
                 for fast data. We describe Muppet, our implementation
                 of MapUpdate. Throughout the description we highlight
                 the key challenges, argue why MapReduce is not well
                 suited to address them, and briefly describe our
                 current solutions. Finally, we describe our experience
                 and lessons learned with Muppet, which has been used
                 extensively at Kosmix and WalmartLabs to power a broad
                 range of applications in social media and e-commerce.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jacques-Silva:2012:BUD,
  author =       "Gabriela Jacques-Silva and Bugra Gedik and Rohit Wagle
                 and Kun-Lung Wu and Vibhore Kumar",
  title =        "Building user-defined runtime adaptation routines for
                 stream processing applications",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1826--1837",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Stream processing applications are deployed as
                 continuous queries that run from the time of their
                 submission until their cancellation. This deployment
                 mode limits developers who need their applications to
                 perform runtime adaptation, such as algorithmic
                 adjustments, incremental job deployment, and
                 application-specific failure recovery. Currently,
                 developers do runtime adaptation by using external
                 scripts and/or by inserting operators into the stream
                 processing graph that are unrelated to the data
                 processing logic. In this paper, we describe a
                 component called orchestrator that allows users to
                 write routines for automatically adapting the
                 application to runtime conditions. Developers build an
                 orchestrator by registering and handling events as well
                 as specifying actuations. Events can be generated due
                 to changes in the system state (e.g., application
                 component failures), built-in system metrics (e.g.,
                 throughput of a connection), or custom application
                 metrics (e.g., quality score). Once the orchestrator
                 receives an event, users can take adaptation actions by
                 using the orchestrator actuation APIs. We demonstrate
                 the use of the orchestrator in IBM's System S in the
                 context of three different applications, illustrating
                 application adaptation to changes on the incoming data
                 distribution, to application failures, and on-demand
                 dynamic composition.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Jiang:2012:MSP,
  author =       "Junchen Jiang and Hongji Bao and Edward Y. Chang and
                 Yuqian Li",
  title =        "{MOIST}: a scalable and parallel moving object indexer
                 with school tracking",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1838--1849",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Location-Based Service (LBS) is rapidly becoming the
                 next ubiquitous technology for a wide range of mobile
                 applications. To support applications that demand
                 nearest-neighbor and history queries, an LBS spatial
                 indexer must be able to efficiently update, query,
                 archive and mine location records, which can be in
                 contention with each other. In this work, we propose
                 MOIST, whose baseline is a recursive spatial
                 partitioning indexer built upon BigTable. To reduce
                 update and query contention, MOIST groups nearby
                 objects of similar trajectory into the same school, and
                 keeps track of only the history of school leaders. This
                 dynamic clustering scheme can eliminate redundant
                 updates and hence reduce update latency. To improve
                 history query processing, MOIST keeps some history data
                 in memory, while it flushes aged data onto parallel
                 disks in a locality-preserving way. Through
                 experimental studies, we show that MOIST can support
                 highly efficient nearest-neighbor and history queries
                 and can scale well with an increasing number of users
                 and update frequency.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Ports:2012:SSI,
  author =       "Dan R. K. Ports and Kevin Grittner",
  title =        "Serializable snapshot isolation in {PostgreSQL}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1850--1861",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper describes our experience implementing
                 PostgreSQL's new serializable isolation level. It is
                 based on the recently-developed Serializable Snapshot
                 Isolation (SSI) technique. This is the first
                 implementation of SSI in a production database release
                 as well as the first in a database that did not
                 previously have a lock-based serializable isolation
                 level. We reflect on our experience and describe how we
                 overcame some of the resulting challenges, including
                 the implementation of a new lock manager, a technique
                 for ensuring memory usage is bounded, and integration
                 with other PostgreSQL features. We also introduce an
                 extension to SSI that improves performance for
                 read-only transactions. We evaluate PostgreSQL's
                 serializable isolation level using several benchmarks
                 and show that it achieves performance only slightly
                 below that of snapshot isolation, and significantly
                 outperforms the traditional two-phase locking approach
                 on read-intensive workloads.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Murthy:2012:EEU,
  author =       "Karin Murthy and Prasad M. Deshpande and Atreyee Dey
                 and Ramanujam Halasipuram and Mukesh Mohania and P.
                 Deepak and Jennifer Reed and Scott Schumacher",
  title =        "Exploiting evidence from unstructured data to enhance
                 master data management",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1862--1873",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Master data management (MDM) integrates data from
                 multiple structured data sources and builds a
                 consolidated 360-degree view of business entities such
                 as customers and products. Today's MDM systems are not
                 prepared to integrate information from unstructured
                 data sources, such as news reports, emails, call-center
                 transcripts, and chat logs. However, those unstructured
                 data sources may contain valuable information about the
                 same entities known to MDM from the structured data
                 sources. Integrating information from unstructured data
                 into MDM is challenging as textual references to
                 existing MDM entities are often incomplete and
                 imprecise and the additional entity information
                 extracted from text should not impact the
                 trustworthiness of MDM data. In this paper, we present
                 an architecture for making MDM text-aware and showcase
                 its implementation as IBM Info-Sphere MDM Extension for
                 Unstructured Text Correlation, an add-on to IBM
                 InfoSphere Master Data Management Standard Edition. We
                 highlight how MDM benefits from additional evidence
                 found in documents when doing entity resolution and
                 relationship discovery. We experimentally demonstrate
                 the feasibility of integrating information from
                 unstructured data sources into MDM.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2012:AOW,
  author =       "Lili Wu and Roshan Sumbaly and Chris Riccomini and
                 Gordon Koo and Hyung Jin Kim and Jay Kreps and Sam
                 Shah",
  title =        "{Avatara}: {OLAP} for web-scale analytics products",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1874--1877",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Multidimensional data generated by members on websites
                 has seen massive growth in recent years. OLAP is a
                 well-suited solution for mining and analyzing this
                 data. Providing insights derived from this analysis has
                 become crucial for these websites to give members
                 greater value. For example, LinkedIn, the largest
                 professional social network, provides its professional
                 members rich analytics features like ``Who's Viewed My
                 Profile?'' and ``Who's Viewed This Job?'' The data
                 behind these features form cubes that must be
                 efficiently served at scale, and can be neatly sharded
                 to do so. To serve our growing 160 million member base,
                 we built a scalable and fast OLAP serving system called
                 Avatara to solve this many, small cubes problem. At
                 LinkedIn, Avatara has been powering several analytics
                 features on the site for the past two years.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kolb:2012:DED,
  author =       "Lars Kolb and Andreas Thor and Erhard Rahm",
  title =        "{Dedoop}: efficient deduplication with {Hadoop}",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1878--1881",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "We demonstrate a powerful and easy-to-use tool called
                 Dedoop ({$<$}u{$>$}De{$<$}/u{$>$}duplication with
                 Ha{$<$}u{$>$}doop{$<$}/u{$>$}) for MapReduce-based
                 entity resolution (ER) of large datasets. Dedoop
                 supports a browser-based specification of complex ER
                 workflows including blocking and matching steps as well
                 as the optional use of machine learning for the
                 automatic generation of match classifiers. Specified
                 workflows are automatically translated into MapReduce
                 jobs for parallel execution on different Hadoop
                 clusters. To achieve high performance Dedoop supports
                 several advanced load balancing strategies.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liu:2012:MBD,
  author =       "Xiufeng Liu and Christian Thomsen and Torben Bach
                 Pedersen",
  title =        "{MapReduce}-based dimensional {ETL} made easy",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1882--1885",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This paper demonstrates ETLMR, a novel dimensional
                 Extract--Transform--Load (ETL) programming framework
                 that uses Map-Reduce to achieve scalability. ETLMR has
                 built-in native support of data warehouse (DW) specific
                 constructs such as star schemas, snowflake schemas, and
                 slowly changing dimensions (SCDs). This makes it
                 possible to build MapReduce-based dimensional ETL flows
                 very easily. The ETL process can be configured with
                 only few lines of code. We will demonstrate the
                 concrete steps in using ETLMR to load data into a
                 (partly snowflaked) DW schema. This includes
                 configuration of data sources and targets, dimension
                 processing schemes, fact processing, and deployment. In
                 addition, we also present the scalability on large data
                 sets.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Xu:2012:CIE,
  author =       "Huiqi Xu and Zhen Li and Shumin Guo and Keke Chen",
  title =        "{CloudVista}: interactive and economical visual
                 cluster analysis for big data in the cloud",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1886--1889",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Analysis of big data has become an important problem
                 for many business and scientific applications, among
                 which clustering and visualizing clusters in big data
                 raise some unique challenges. This demonstration
                 presents the CloudVista prototype system to address the
                 problems with big data caused by using existing data
                 reduction approaches. It promotes a whole-big-data
                 visualization approach that preserves the details of
                 clustering structure. The prototype system has several
                 merits. (1) Its visualization model is naturally
                 parallel, which guarantees the scalability. (2) The
                 visual frame structure minimizes the data transferred
                 between the cloud and the client. (3) The RandGen
                 algorithm is used to achieve a good balance between
                 interactivity and batch processing. (4) This approach
                 is also designed to minimize the financial cost of
                 interactive exploration in the cloud. The demonstration
                 will highlight the problems with existing approaches
                 and show the advantages of the CloudVista approach. The
                 viewers will have the chance to play with the
                 CloudVista prototype system and compare the
                 visualization results generated with different
                 approaches.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alexandrov:2012:MSE,
  author =       "Alexander Alexandrov and Kostas Tzoumas and Volker
                 Markl",
  title =        "{Myriad}: scalable and expressive data generation",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1890--1893",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "The current research focus on Big Data systems calls
                 for a rethinking of data generation methods. The
                 traditional sequential data generation approach is not
                 well suited to large-scale systems as generating a
                 terabyte of data may require days or even weeks
                 depending on the number of constraints imposed on the
                 generated model. We demonstrate Myriad, a new data
                 generation toolkit that enables the specification of
                 semantically rich data generator programs that can
                 scale out linearly in a shared-nothing environment.
                 Data generation programs built on top of Myriad
                 implement an efficient parallel execution strategy
                 leveraged by the extensive use of pseudo-random number
                 generators with random access support.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Wu:2012:DDC,
  author =       "Eugene Wu and Samuel Madden and Michael Stonebraker",
  title =        "A demonstration of {DBWipes}: clean as you query",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1894--1897",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "As data analytics becomes mainstream, and the
                 complexity of the underlying data and computation
                 grows, it will be increasingly important to provide
                 tools that help analysts understand the underlying
                 reasons when they encounter errors in the result. While
                 data provenance has been a large step in providing
                 tools to help debug complex workflows, its current form
                 has limited utility when debugging aggregation
                 operators that compute a single output from a large
                 collection of inputs. Traditional provenance will
                 return the entire input collection, which has very low
                 precision. In contrast, users are seeking precise
                 descriptions of the inputs that caused the errors. We
                 propose a Ranked Provenance System, which identifies
                 subsets of inputs that influenced the output error,
                 describes each subset with human readable predicates
                 and orders them by contribution to the error. In this
                 demonstration, we will present DBWipes, a novel data
                 cleaning system that allows users to execute aggregate
                 queries, and interactively detect, understand, and
                 clean errors in the query results. Conference attendees
                 will explore anomalies in campaign donations from the
                 current US presidential election and in readings from a
                 54-node sensor deployment.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Alsubaiee:2012:AOS,
  author =       "Sattam Alsubaiee and Yasser Altowim and Hotham
                 Altwaijry and Alexander Behm and Vinayak Borkar and
                 Yingyi Bu and Michael Carey and Raman Grover and
                 Zachary Heilbron and Young-Seok Kim and Chen Li and
                 Nicola Onose and Pouria Pirzadeh and Rares Vernica and
                 Jian Wen",
  title =        "{ASTERIX}: an open source system for ``Big {Data'}'
                 management and analysis (demo)",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1898--1901",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "At UC Irvine, we are building a next generation
                 parallel database system, called ASTERIX, as our
                 approach to addressing today's ``Big Data'' management
                 challenges. ASTERIX aims to combine time-tested
                 principles from parallel database systems with those of
                 the Web-scale computing community, such as fault
                 tolerance for long running jobs. In this demo, we
                 present a whirlwind tour of ASTERIX, highlighting a few
                 of its key features. We will demonstrate examples of
                 our data definition language to model semi-structured
                 data, and examples of interesting queries using our
                 declarative query language. In particular, we will show
                 the capabilities of ASTERIX for answering geo-spatial
                 queries and fuzzy queries, as well as ASTERIX' data
                 feed construct for continuously ingesting data.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Agarwal:2012:BDI,
  author =       "Sameer Agarwal and Anand P. Iyer and Aurojit Panda and
                 Samuel Madden and Barzan Mozafari and Ion Stoica",
  title =        "Blink and it's done: interactive queries on very large
                 data",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1902--1905",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In this demonstration, we present BlinkDB, a massively
                 parallel, sampling-based approximate query processing
                 framework for running interactive queries on large
                 volumes of data. The key observation in BlinkDB is that
                 one can make reasonable decisions in the absence of
                 perfect answers. BlinkDB extends the Hive/HDFS stack
                 and can handle the same set of SPJA (selection,
                 projection, join and aggregate) queries as supported by
                 these systems. BlinkDB provides real-time answers along
                 with statistical error guarantees, and can scale to
                 petabytes of data and thousands of machines in a
                 fault-tolerant manner. Our experiments using the TPC-H
                 benchmark and on an anonymized real-world video content
                 distribution workload from Conviva Inc. show that
                 BlinkDB can execute a wide range of queries up to 150x
                 faster than Hive on MapReduce and 10--150x faster than
                 Shark (Hive on Spark) over tens of terabytes of data
                 stored across 100 machines, all with an error of
                 2--10\%.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Roy:2012:MGD,
  author =       "Abhishek Roy and Yanlei Diao and Evan Mauceli and
                 Yiping Shen and Bai-Lin Wu",
  title =        "Massive genomic data processing and deep analysis",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1906--1909",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Today large sequencing centers are producing genomic
                 data at the rate of 10 terabytes a day and require
                 complicated processing to transform massive amounts of
                 noisy raw data into biological information. To address
                 these needs, we develop a system for end-to-end
                 processing of genomic data, including alignment of
                 short read sequences, variation discovery, and deep
                 analysis. We also employ a range of quality control
                 mechanisms to improve data quality and parallel
                 processing techniques for performance. In the demo, we
                 will use real genomic data to show details of data
                 transformation through the workflow, the usefulness of
                 end results (ready for use as testable hypotheses), the
                 effects of our quality control mechanisms and improved
                 algorithms, and finally performance improvement.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Liarou:2012:MDO,
  author =       "Erietta Liarou and Stratos Idreos and Stefan Manegold
                 and Martin Kersten",
  title =        "{MonetDB\slash DataCell}: online analytics in a
                 streaming column-store",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1910--1913",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "In DataCell, we design streaming functionalities in a
                 modern relational database kernel which targets big
                 data analytics. This includes exploitation of both its
                 storage/execution engine and its optimizer
                 infrastructure. We investigate the opportunities and
                 challenges that arise with such a direction and we show
                 that it carries significant advantages for modern
                 applications in need for online analytics such as web
                 logs, network monitoring and scientific data
                 management. The major challenge then becomes the
                 efficient support for specialized stream features,
                 e.g., multi-query processing and incremental
                 window-based processing as well as exploiting standard
                 DBMS functionalities in a streaming environment such as
                 indexing. This demo presents DataCell, an extension of
                 the MonetDB open-source column-store for online
                 analytics. The demo gives users the opportunity to
                 experience the features of DataCell such as processing
                 both stream and persistent data and performing window
                 based processing. The demo provides a visual interface
                 to monitor the critical system components, e.g., how
                 query plans transform from typical DBMS query plans to
                 online query plans, how data flows through the query
                 plans as the streams evolve, how DataCell maintains
                 intermediate results in columnar form to avoid repeated
                 evaluation of the same stream portions, etc. The demo
                 also provides the ability to interactively set the test
                 scenarios and various DataCell knobs.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Cao:2012:SSE,
  author =       "Xin Cao and Gao Cong and Christian S. Jensen and Jun
                 Jie Ng and Beng Chin Ooi and Nhan-Tue Phan and Dingming
                 Wu",
  title =        "{SWORS}: a system for the efficient retrieval of
                 relevant spatial web objects",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1914--1917",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Spatial web objects that possess both a geographical
                 location and a textual description are gaining in
                 prevalence. This gives prominence to spatial keyword
                 queries that exploit both location and textual
                 arguments. Such queries are used in many web services
                 such as yellow pages and maps services. We present
                 SWORS, the Spatial Web Object Retrieval System, that is
                 capable of efficiently retrieving spatial web objects
                 that satisfy spatial keyword queries. Specifically,
                 SWORS supports two types of queries: (a) the
                 location-aware top-$k$ text retrieval (L $k$ T) query
                 that retrieves $k$ individual spatial web objects
                 taking into account query location proximity and text
                 relevancy; (b) the spatial keyword group (SKG) query
                 that retrieves a group of objects that cover the query
                 keywords and are nearest to the query location and have
                 the shortest inter-object distances. SWORS provides
                 browser-based interfaces for desktop and laptop
                 computers and provides a client application for mobile
                 devices. The interfaces and the client enable users to
                 formulate queries and view the query results on a map.
                 The server side stores the data and processes the
                 queries. We use three real-life data sets to
                 demonstrate the functionality and performance of
                 SWORS.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Morishima:2012:CCD,
  author =       "Atsuyuki Morishima and Norihide Shinagawa and Tomomi
                 Mitsuishi and Hideto Aoki and Shun Fukusumi",
  title =        "{CyLog\slash Crowd4U}: a declarative platform for
                 complex data-centric crowdsourcing",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1918--1921",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "This demo presents a principled approach to the
                 problems of data-centric human/machine computations
                 with Crowd4U, a crowdsourcing platform equipped with a
                 suite of tools for rapid development of crowdsourcing
                 applications. Using the demo, we show that declarative
                 database abstraction can be used as a powerful tool to
                 design, implement, and analyze data-centric
                 crowdsourcing applications. The power of Crowd4U comes
                 from CyLog, a database abstraction that handles complex
                 data-centric human/machine computations. CyLog is a
                 Datalog-like language that incorporates a principled
                 feedback system for humans at the language level so
                 that the semantics of the computation not closed in
                 machines can be defined based on the game theory. We
                 believe that the demo clearly shows that database
                 abstraction can be a promising basis for designing
                 complex data-centric applications requiring
                 human/machine computations.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Silva:2012:EDS,
  author =       "Yasin N. Silva and Spencer Pearson",
  title =        "Exploiting database similarity joins for metric
                 spaces",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1922--1925",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Similarity Joins are recognized among the most useful
                 data processing and analysis operations and are
                 extensively used in multiple application domains. They
                 retrieve all data pairs whose distances are smaller
                 than a predefined threshold $\epsilon$. Multiple
                 Similarity Join algorithms and implementation
                 techniques have been proposed. They range from
                 out-of-database approaches for only in-memory and
                 external memory data to techniques that make use of
                 standard database operators to answer similarity joins.
                 Recent work has shown that this operation can be
                 efficiently implemented as a physical database
                 operator. However, the proposed operator only support
                 1D numeric data. This paper presents DBSimJoin, a
                 physical Similarity Join database operator for datasets
                 that lie in any metric space. DBSimJoin is a
                 non-blocking operator that prioritizes the early
                 generation of results. We implemented the proposed
                 operator in PostgreSQL, an open source database system.
                 We show how this operator can be used in multiple
                 real-world data analysis scenarios with multiple data
                 types and distance functions. Particularly, we show the
                 use of DBSimJoin to identify similar images represented
                 as feature vectors, and similar publications in a
                 bibliographic database. We also show that DBSimJoin
                 scales very well when important parameters, e.g., e,
                 data size, increase.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Gawade:2012:SPI,
  author =       "Mrunal Gawade and Martin Kersten",
  title =        "{Stethoscope}: a platform for interactive visual
                 analysis of query execution plans",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  number =       "12",
  pages =        "1926--1929",
  month =        aug,
  year =         "2012",
  CODEN =        "????",
  ISSN =         "2150-8097",
  bibdate =      "Tue Nov 6 16:43:21 MST 2012",
  bibsource =    "http://portal.acm.org/;
                 http://www.math.utah.edu/pub/tex/bib/vldbe.bib",
  abstract =     "Searching for the performance bottleneck in an
                 execution trace is an error prone and time consuming
                 activity. Existing tools offer some comfort by
                 providing a visual representation of trace for
                 analysis. In this paper we present the Stethoscope, an
                 interactive visual tool to inspect and analyze columnar
                 database query performance, both online and offline.
                 It's unique interactive animated interface capitalizes
                 the large data-flow graph representation of a query
                 execution plan, augmented with query execution trace
                 information. We demonstrate features of Stethoscope for
                 both online and offline analysis of long running
                 queries. It helps in understanding where time goes, how
                 optimizers perform, and how parallel processing on
                 multi-core systems is exploited.",
  acknowledgement = ack-nhfb,
  fjournal =     "Proceedings of the VLDB Endowment",
}

@Article{Kotsifakos:2012:HSS,
  author =       "Alexios Kotsifakos and Panagiotis Papapetrou and
                 Jaakko Hollm{\'e}n and Dimitrios Gunopulos and Vassilis
                 Athitsos and George Kollios",
  title =        "{Hum-a-song}: a subsequence matching with
                 gaps-range-tolerances query-by-humming system",
  journal =      j-PROC-VLDB-ENDOWMENT,
  volume =       "5",
  numbe