{"id":"https://openalex.org/W4366502978","doi":"https://doi.org/10.14778/3583140.3583164","title":"Robust Query Driven Cardinality Estimation under Changing Workloads","display_name":"Robust Query Driven Cardinality Estimation under Changing Workloads","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4366502978","doi":"https://doi.org/10.14778/3583140.3583164"},"language":"en","primary_location":{"id":"doi:10.14778/3583140.3583164","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3583140.3583164","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5018121640","display_name":"Parimarjan Negi","orcid":"https://orcid.org/0000-0002-8442-9159"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Parimarjan Negi","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002733135","display_name":"Zi\u2010Niu Wu","orcid":"https://orcid.org/0000-0002-4405-0865"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziniu Wu","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046188245","display_name":"Andreas Kipf","orcid":"https://orcid.org/0000-0003-3463-0564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Kipf","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002085554","display_name":"Nesime Tatbul","orcid":"https://orcid.org/0000-0002-0416-7022"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nesime Tatbul","raw_affiliation_strings":["MIT CSAIL, Intel Labs"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL, Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025731013","display_name":"Ryan Marcus","orcid":"https://orcid.org/0000-0002-1279-1124"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Marcus","raw_affiliation_strings":["MIT CSAIL, Intel Labs"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL, Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Madden","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101669321","display_name":"Mohammad Alizadeh","orcid":"https://orcid.org/0000-0002-2002-2632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Alizadeh","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5018121640"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.0753,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.9885306,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"16","issue":"6","first_page":"1520","last_page":"1533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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":0.9930999875068665,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9822999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8289332389831543},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.5910447835922241},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5903274416923523},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5739454627037048},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5468298196792603},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5223773121833801},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4844196140766144},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.46497440338134766},{"id":"https://openalex.org/keywords/column","display_name":"Column (typography)","score":0.43926316499710083},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4378988742828369},{"id":"https://openalex.org/keywords/spatial-query","display_name":"Spatial query","score":0.4352136254310608},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4223329424858093},{"id":"https://openalex.org/keywords/web-query-classification","display_name":"Web query classification","score":0.41254565119743347},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3911958336830139},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.3411480784416199},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2601397633552551},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2596375346183777}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289332389831543},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.5910447835922241},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5903274416923523},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5739454627037048},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5468298196792603},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5223773121833801},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4844196140766144},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.46497440338134766},{"id":"https://openalex.org/C2780551164","wikidata":"https://www.wikidata.org/wiki/Q2306599","display_name":"Column (typography)","level":3,"score":0.43926316499710083},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4378988742828369},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.4352136254310608},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4223329424858093},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.41254565119743347},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3911958336830139},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3411480784416199},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2601397633552551},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2596375346183777},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3583140.3583164","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3583140.3583164","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2132823934","https://openalex.org/W2168865746","https://openalex.org/W2396309311","https://openalex.org/W2396635388","https://openalex.org/W2906910993","https://openalex.org/W2939293933","https://openalex.org/W2946026089","https://openalex.org/W2950833175","https://openalex.org/W2955798121","https://openalex.org/W2969294089","https://openalex.org/W2991530444","https://openalex.org/W3013555795","https://openalex.org/W3023577490","https://openalex.org/W3024738030","https://openalex.org/W3030994385","https://openalex.org/W3082526573","https://openalex.org/W3097225903","https://openalex.org/W3100077023","https://openalex.org/W3111141572","https://openalex.org/W3124277639","https://openalex.org/W3129744650","https://openalex.org/W3173622057","https://openalex.org/W3183953540","https://openalex.org/W3197977787","https://openalex.org/W3198024709","https://openalex.org/W4226086155","https://openalex.org/W4242587584","https://openalex.org/W4281754544","https://openalex.org/W4282546806","https://openalex.org/W4289706945"],"related_works":["https://openalex.org/W2096359267","https://openalex.org/W2350026801","https://openalex.org/W2388669825","https://openalex.org/W2901901036","https://openalex.org/W2169364631","https://openalex.org/W2011795509","https://openalex.org/W2095149003","https://openalex.org/W1993470918","https://openalex.org/W2337762748","https://openalex.org/W2372938158"],"abstract_inverted_index":{"Query":[0],"driven":[1,306],"cardinality":[2],"estimation":[3],"models":[4,34,64,86,297,307],"learn":[5],"from":[6,165],"a":[7,199,206],"historical":[8],"log":[9],"of":[10,30,91,174,216],"queries.":[11],"They":[12],"are":[13,24,140],"lightweight,":[14],"having":[15],"low":[16],"storage":[17],"requirements,":[18],"fast":[19],"inference":[20],"and":[21,23,55,71,78,195,242,258,269],"training,":[22],"easily":[25],"adaptable":[26],"for":[27],"any":[28],"kind":[29],"query.":[31],"Unfortunately,":[32],"such":[33],"can":[35,177,308],"suffer":[36],"unpredictably":[37],"bad":[38],"performance":[39],"under":[40],"workload":[41,69,92,97,208,277],"drift,":[42,70],"i.e.,":[43],"if":[44],"the":[45,61,75,89,120,227,264,292],"query":[46,76,127,144,244,305],"pattern":[47],"or":[48,105,113,145],"data":[49,146,182,256],"changes.":[50],"This":[51,118],"makes":[52],"them":[53],"unreliable":[54],"hard":[56],"to":[57,68,74,83,88,122,158,180,224,226,239],"deploy.":[58],"We":[59,184,250,262],"analyze":[60],"reasons":[62],"why":[63],"become":[65],"unpredictable":[66],"due":[67],"introduce":[72,151],"modifications":[73],"representation":[77],"neural":[79],"network":[80],"training":[81],"techniques":[82,204,282],"make":[84,123],"query-driven":[85],"robust":[87,132],"effects":[90],"drift.":[93],"First,":[94],"we":[95,150,170,267],"emulate":[96],"drift":[98,147,278],"in":[99,291],"queries":[100,215,236],"involving":[101],"some":[102,111],"unseen":[103],"tables":[104,220],"columns":[106],"by":[107,246],"randomly":[108],"masking":[109],"out":[110],"table":[112],"column":[114],"features":[115,133,157],"during":[116],"training.":[117],"forces":[119],"model":[121,200],"predictions":[124],"with":[125,202,210,237,255],"missing":[126],"information,":[128],"relying":[129],"more":[130,229,275],"on":[131,135,205],"based":[134],"up-to-date":[136],"DBMS":[137],"statistics":[138],"that":[139],"useful":[141],"even":[142,290],"when":[143],"happens.":[148],"Second,":[149],"join":[152],"bitmaps,":[153],"which":[154,234],"extends":[155],"sampling-based":[156],"be":[159,178],"consistent":[160],"across":[161,192,259],"joins":[162],"using":[163],"ideas":[164,176],"sideways":[166],"information":[167],"passing.":[168],"Finally,":[169],"show":[171,185,251],"how":[172],"both":[173],"these":[175,281],"adapted":[179],"handle":[181],"updates.":[183],"significantly":[186],"greater":[187],"generalization":[188],"than":[189,301,312],"past":[190],"works":[191],"different":[193],"workloads":[194],"databases.":[196],"For":[197],"instance,":[198],"trained":[201],"our":[203,296],"simple":[207],"(JOBLight-train),":[209],"40":[211],"k":[212],"synthetically":[213],"generated":[214],"at":[217],"most":[218,293],"3":[219],"each,":[221],"is":[222],"able":[223],"generalize":[225],"much":[228,286,310],"complex":[230],"Join":[231],"Order":[232],"Benchmark,":[233],"include":[235],"up":[238],"16":[240],"tables,":[241],"improve":[243,285],"runtimes":[245],"2\u00d7":[247],"over":[248,287],"PostgreSQL.":[249,288,313],"similar":[252],"robustness":[253],"results":[254],"updates,":[257],"other":[260],"workloads.":[261],"discuss":[263],"situations":[265],"where":[266,280],"expect,":[268],"see,":[270],"improvements,":[271],"as":[272,274],"well":[273],"challenging":[276,294],"scenarios":[279],"do":[283],"not":[284],"However,":[289],"scenarios,":[295],"never":[298],"perform":[299],"worse":[300,311],"PostgreSQL,":[302],"while":[303],"standard":[304],"get":[309]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}