{"id":"https://openalex.org/W2168865746","doi":"https://doi.org/10.1145/375663.375727","title":"Selectivity estimation using probabilistic models","display_name":"Selectivity estimation using probabilistic models","publication_year":2001,"publication_date":"2001-05-01","ids":{"openalex":"https://openalex.org/W2168865746","doi":"https://doi.org/10.1145/375663.375727","mag":"2168865746"},"language":"en","primary_location":{"id":"doi:10.1145/375663.375727","doi":"https://doi.org/10.1145/375663.375727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/375663.375727","pdf_url":null,"source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2001 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5086169451","display_name":"Lise C. Getoor","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lise Getoor","raw_affiliation_strings":["Computer Science Dept., Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111968059","display_name":"Benjamin Taskar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Taskar","raw_affiliation_strings":["Computer Science Dept., Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051658526","display_name":"Daphne Koller","orcid":"https://orcid.org/0000-0002-2361-6479","observed_orcids":["https://orcid.org/0000-0002-2361-6479","https://orcid.org/0009-0007-1645-951X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daphne Koller","raw_affiliation_strings":["Computer Science Dept., Stanford University, Stanford, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept., Stanford University, Stanford, CA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":6.1721,"has_fulltext":false,"cited_by_count":262,"citation_normalized_percentile":{"value":0.9646539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.03310000151395798,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11106","display_name":"Data Management and Algorithms","score":0.009200000204145908,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/selectivity-estimation","display_name":"selectivity estimation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/probabilistic-relational-models","display_name":"probabilistic relational models","score":0.9879999756813049},{"id":"https://openalex.org/keywords/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.8510000109672546},{"id":"https://openalex.org/keywords/bayesian-networks","display_name":"Bayesian networks","score":0.8690000176429749},{"id":"https://openalex.org/keywords/cost-based-query-optimization","display_name":"cost-based query optimization","score":0.7490000128746033},{"id":"https://openalex.org/keywords/approximate-query-processing","display_name":"approximate query processing","score":0.9909999966621399},{"id":"https://openalex.org/keywords/join-size-estimation","display_name":"join size estimation","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807050347328186},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7418645620346069},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.6306058168411255},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6182934641838074},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5744122266769409},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5643636584281921},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5033888220787048},{"id":"https://openalex.org/C174539288","wikidata":"https://www.wikidata.org/wiki/Q7246853","display_name":"Probabilistic database","level":4,"score":0.47098299860954285},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.46392402052879333},{"id":"https://openalex.org/C4969071","wikidata":"https://www.wikidata.org/wiki/Q7316353","display_name":"Result set","level":3,"score":0.4583210051059723},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4044697880744934},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36047983169555664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2593045234680176},{"id":"https://openalex.org/C12439846","wikidata":"https://www.wikidata.org/wiki/Q4809258","display_name":"Database theory","level":3,"score":0.2088271975517273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1970643699169159},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/375663.375727","doi":"https://doi.org/10.1145/375663.375727","is_oa":false,"landing_page_url":"https://doi.org/10.1145/375663.375727","pdf_url":null,"source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2001 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.5550","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.5550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/people/getoor/papers/sigmod01.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.5924","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.5924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://robotics.stanford.edu/~koller/papers/sigmod01.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W26772505","https://openalex.org/W148724713","https://openalex.org/W1485908346","https://openalex.org/W1501299699","https://openalex.org/W1529618148","https://openalex.org/W1530964327","https://openalex.org/W1555273987","https://openalex.org/W1573686114","https://openalex.org/W1581547316","https://openalex.org/W1589269155","https://openalex.org/W1593793857","https://openalex.org/W1615454278","https://openalex.org/W1722352548","https://openalex.org/W1746680969","https://openalex.org/W1968829657","https://openalex.org/W1998244781","https://openalex.org/W2020584928","https://openalex.org/W2021850646","https://openalex.org/W2024974612","https://openalex.org/W2072419714","https://openalex.org/W2085988990","https://openalex.org/W2099111195","https://openalex.org/W2110111529","https://openalex.org/W2110557355","https://openalex.org/W2126185296","https://openalex.org/W2147232895","https://openalex.org/W2159080219","https://openalex.org/W4234667859","https://openalex.org/W4241185933","https://openalex.org/W4250143236"],"related_works":["https://openalex.org/W7099502181","https://openalex.org/W2089059416","https://openalex.org/W2396635388","https://openalex.org/W3030994385","https://openalex.org/W3212564838","https://openalex.org/W3045108149","https://openalex.org/W2924111053","https://openalex.org/W2944132009","https://openalex.org/W1963261499","https://openalex.org/W3088258822"],"abstract_inverted_index":{"Estimating":[0],"the":[1,14,64,96,142,153,187],"result":[2],"size":[3],"of":[4,16,63,68,138,141,145,155,175,189,193,218],"complex":[5],"queries":[6,156,195,213],"that":[7,82],"involve":[8],"selection":[9],"on":[10,205],"multiple":[11,69,72,197],"attributes":[12,70,100,106],"and":[13,37,60,104,122,160,214,236],"join":[15,162],"several":[17,206],"relations":[18],"is":[19,148,167],"a":[20,79,102,117,120,125,135,149,172,178,190,215],"difficult":[21],"but":[22],"fundamental":[23],"task":[24,56],"in":[25,31],"database":[26],"query":[27,33,35,39],"processing.":[28],"It":[29],"arises":[30],"cost-based":[32],"optimization,":[34],"profiling,":[36],"approximate":[38],"answering.":[40],"In":[41],"this":[42,55,146],"paper,":[43],"we":[44],"show":[45,123],"how":[46,124],"probabilistic":[47],"graphical":[48,84],"models":[49,86],"can":[50,127,181],"be":[51,128,182],"effectively":[52,185],"used":[53,129,183],"for":[54,115,134,152,202],"as":[57,88],"an":[58,112],"accurate":[59,225],"compact":[61],"approximation":[62],"joint":[65],"frequency":[66],"distribution":[67],"across":[71,107,196],"relations.":[73],"Probabilistic":[74],"Relational":[75],"Models":[76],"(PRMs)":[77],"are":[78],"recent":[80],"development":[81],"extends":[83],"statistical":[85,97],"such":[87],"Bayesian":[89],"Networks":[90],"to":[91,130,170,184,230],"relational":[92],"domains.":[93],"They":[94],"represent":[95],"dependencies":[98],"between":[99,105],"within":[101],"table,":[103],"foreign-key":[108,161],"joins.":[109],"We":[110,199],"provide":[111],"efficient":[113],"algorithm":[114],"constructing":[116],"PRM":[118,126],"front":[119],"database,":[121],"compute":[131],"selectivity":[132,231],"estimates":[133,226],"broad":[136],"class":[137,217],"queries.":[139],"One":[140],"major":[143],"contributions":[144],"work":[147],"unified":[150],"framework":[151],"estimation":[154],"involving":[157],"both":[158,210],"select":[159],"operations.":[163],"Furthermore,":[164],"our":[165,203,221],"approach":[166,204,222],"not":[168],"limited":[169],"answering":[171],"small":[173],"set":[174],"predetermined":[176],"queries;":[177],"single":[179],"model":[180],"estimate":[186],"sizes":[188],"wide":[191],"collection":[192],"potential":[194],"tables.":[198],"present":[200],"results":[201],"real-world":[207],"databases.":[208],"For":[209],"single-table":[211],"multi-attribute":[212],"general":[216],"select-join":[219],"queries,":[220],"produces":[223],"more":[224],"than":[227],"standard":[228],"approaches":[229],"estimation,":[232],"using":[233],"comparable":[234],"space":[235],"time.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":22},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}