{"id":"https://openalex.org/W2162139064","doi":"https://doi.org/10.1145/1142351.1142394","title":"Finding global icebergs over distributed data sets","display_name":"Finding global icebergs over distributed data sets","publication_year":2006,"publication_date":"2006-06-26","ids":{"openalex":"https://openalex.org/W2162139064","doi":"https://doi.org/10.1145/1142351.1142394","mag":"2162139064"},"language":"en","primary_location":{"id":"doi:10.1145/1142351.1142394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142351.1142394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-fifth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047419128","display_name":"Qi Zhao","orcid":"https://orcid.org/0000-0003-3054-8934"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qi (George) Zhao","raw_affiliation_strings":["Georgia Tech"],"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019383096","display_name":"Mitsunori Ogihara","orcid":"https://orcid.org/0000-0002-5690-7854"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitsunori Ogihara","raw_affiliation_strings":["Univ. of Rochester"],"affiliations":[{"raw_affiliation_string":"Univ. of Rochester","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063351917","display_name":"Haixun Wang","orcid":"https://orcid.org/0009-0007-0773-7004"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haixun Wang","raw_affiliation_strings":["IBM T.J Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM T.J Watson Research Center","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101573524","display_name":"Jun Xu","orcid":"https://orcid.org/0009-0006-2358-4098"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun (Jim) Xu","raw_affiliation_strings":["Georgia Tech"],"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047419128"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":2.5441,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.89804302,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"298","last_page":"307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.642604649066925},{"id":"https://openalex.org/keywords/iceberg","display_name":"Iceberg","score":0.6272045373916626},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38625240325927734},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.21189740300178528},{"id":"https://openalex.org/keywords/oceanography","display_name":"Oceanography","score":0.1245543360710144},{"id":"https://openalex.org/keywords/sea-ice","display_name":"Sea ice","score":0.07371312379837036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642604649066925},{"id":"https://openalex.org/C12481700","wikidata":"https://www.wikidata.org/wiki/Q47568","display_name":"Iceberg","level":3,"score":0.6272045373916626},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38625240325927734},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.21189740300178528},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.1245543360710144},{"id":"https://openalex.org/C136894858","wikidata":"https://www.wikidata.org/wiki/Q213926","display_name":"Sea ice","level":2,"score":0.07371312379837036}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1142351.1142394","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142351.1142394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the twenty-fifth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.205","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cc.gatech.edu/~jx/reprints/Pods06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W1540340974","https://openalex.org/W1675727887","https://openalex.org/W1928358804","https://openalex.org/W2003262311","https://openalex.org/W2009090493","https://openalex.org/W2010973140","https://openalex.org/W2023797161","https://openalex.org/W2042587503","https://openalex.org/W2068871408","https://openalex.org/W2069980026","https://openalex.org/W2080234606","https://openalex.org/W2091323212","https://openalex.org/W2099708664","https://openalex.org/W2113139394","https://openalex.org/W2123845384","https://openalex.org/W2124298185","https://openalex.org/W2126540423","https://openalex.org/W2151823597","https://openalex.org/W2152637787","https://openalex.org/W2156632255","https://openalex.org/W2162139064","https://openalex.org/W2164128653","https://openalex.org/W2166767032","https://openalex.org/W2167973519","https://openalex.org/W2496163386","https://openalex.org/W4250544186","https://openalex.org/W4250871362","https://openalex.org/W6684418397"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W205239035","https://openalex.org/W1988952638","https://openalex.org/W2200307848","https://openalex.org/W1990148839","https://openalex.org/W2594414483","https://openalex.org/W2161198985","https://openalex.org/W2936516501","https://openalex.org/W3214910983","https://openalex.org/W99746984"],"abstract_inverted_index":{"Finding":[0],"icebergs":[1,103],"\u2013":[2,13],"items":[3,119],"whose":[4],"frequency":[5],"of":[6,22,25,50,164,171,194],"occurrence":[7],"is":[8,14,176],"above":[9],"a":[10,19,34,47,69,144,148,157],"certain":[11],"threshold":[12],"an":[15,162],"important":[16,115],"problem":[17],"with":[18],"wide":[20],"range":[21],"applications.":[23],"Most":[24],"the":[26,59,73,90,98,153,168,191],"existing":[27],"work":[28],"focuses":[29],"on":[30],"iceberg":[31],"queries":[32],"at":[33,124,160],"single":[35],"node.":[36,126],"However,":[37],"in":[38,113],"many":[39,114],"real-life":[40],"applications,":[41,116],"data":[42,66],"sets":[43],"are":[44],"distributed":[45],"across":[46],"large":[48],"number":[49],"nodes.":[51],"Two":[52],"na\u00efve":[53,169],"approaches":[54],"might":[55],"be":[56,122],"considered.":[57],"In":[58,89,127,151],"first,":[60],"each":[61,92],"node":[62,93],"ships":[63],"its":[64],"entire":[65],"set":[67],"to":[68,79,104,141,178],"central":[70,74,99],"server,":[71],"and":[72,97,138,147,186],"server":[75,100],"uses":[76],"single-node":[77],"algorithms":[78],"find":[80,105],"icebergs.":[81,107],"But":[82,108],"it":[83,109],"may":[84,110,120],"incur":[85],"prohibitive":[86],"communication":[87,158],"overhead.":[88],"second,":[91],"submits":[94],"local":[95,102],"icebergs,":[96],"combines":[101],"global":[106],"fail":[111],"because":[112],"globally":[117],"frequent":[118,123],"not":[121],"any":[125],"this":[128,142],"work,":[129],"we":[130,189],"propose":[131],"two":[132],"novel":[133],"schemes":[134],"that":[135],"provide":[136],"accurate":[137],"efficient":[139],"solutions":[140],"problem:":[143],"sampling-based":[145],"scheme":[146,155,170],"counting-sketch-based":[149],"scheme.":[150],"particular,":[152],"latter":[154],"incurs":[156],"cost":[159],"least":[161],"order":[163],"magnitude":[165],"smaller":[166],"than":[167],"shipping":[172],"all":[173],"data,":[174],"yet":[175],"able":[177],"achieve":[179],"very":[180],"high":[181],"accuracy.":[182],"Through":[183],"rigorous":[184],"theoretical":[185],"experimental":[187],"analysis":[188],"establish":[190],"statistical":[192],"properties":[193],"our":[195],"proposed":[196],"algorithms,":[197],"including":[198],"their":[199],"accuracy":[200],"bounds.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}