{"id":"https://openalex.org/W4380433194","doi":"https://doi.org/10.1145/3588721","title":"FactorJoin: A New Cardinality Estimation Framework for Join Queries","display_name":"FactorJoin: A New Cardinality Estimation Framework for Join Queries","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433194","doi":"https://doi.org/10.1145/3588721"},"language":"en","primary_location":{"id":"doi:10.1145/3588721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588721","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588721","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3588721","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060968223","display_name":"Ziniu Wu","orcid":"https://orcid.org/0000-0002-5487-952X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ziniu Wu","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018121640","display_name":"Parimarjan Negi","orcid":"https://orcid.org/0000-0002-8442-9159"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parimarjan Negi","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669321","display_name":"Mohammad Alizadeh","orcid":"https://orcid.org/0000-0002-2002-2632"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Alizadeh","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034086130","display_name":"Tim Kraska","orcid":"https://orcid.org/0009-0003-2414-2759"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Kraska","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037742794","display_name":"Samuel Madden","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Madden","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060968223"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":8.9147,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.98629882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9993000030517578,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/joins","display_name":"Joins","score":0.7733046412467957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701073884963989},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6910682916641235},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.530424177646637},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.4865480959415436},{"id":"https://openalex.org/keywords/sort-merge-join","display_name":"Sort-merge join","score":0.47266730666160583},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.469748318195343},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4446893632411957},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4303654730319977},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.411684513092041},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3394627273082733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11805099248886108}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.7733046412467957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701073884963989},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6910682916641235},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.530424177646637},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.4865480959415436},{"id":"https://openalex.org/C203570394","wikidata":"https://www.wikidata.org/wiki/Q4060688","display_name":"Sort-merge join","level":3,"score":0.47266730666160583},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.469748318195343},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4446893632411957},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4303654730319977},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.411684513092041},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3394627273082733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11805099248886108},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588721","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588721","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3588721","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3588721","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3588721","source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"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 ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6100000143051147,"display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G312414007","display_name":null,"funder_award_id":"1900933","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380433194.pdf","grobid_xml":"https://content.openalex.org/works/W4380433194.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1511986666","https://openalex.org/W1565231908","https://openalex.org/W1581547316","https://openalex.org/W1968829657","https://openalex.org/W2001453010","https://openalex.org/W2007069074","https://openalex.org/W2007451827","https://openalex.org/W2010890196","https://openalex.org/W2011679994","https://openalex.org/W2040370888","https://openalex.org/W2075712468","https://openalex.org/W2081728040","https://openalex.org/W2089059416","https://openalex.org/W2102166438","https://openalex.org/W2137813581","https://openalex.org/W2144661390","https://openalex.org/W2146492010","https://openalex.org/W2150859678","https://openalex.org/W2151310484","https://openalex.org/W2153329411","https://openalex.org/W2163166770","https://openalex.org/W2168865746","https://openalex.org/W2396309311","https://openalex.org/W2396635388","https://openalex.org/W2413967352","https://openalex.org/W2585424461","https://openalex.org/W2766026698","https://openalex.org/W2790625403","https://openalex.org/W2798499404","https://openalex.org/W2911540814","https://openalex.org/W2950833175","https://openalex.org/W2955798121","https://openalex.org/W2963066364","https://openalex.org/W3013555795","https://openalex.org/W3021702690","https://openalex.org/W3024784979","https://openalex.org/W3029535034","https://openalex.org/W3030639942","https://openalex.org/W3030994385","https://openalex.org/W3041888157","https://openalex.org/W3097225903","https://openalex.org/W3099158806","https://openalex.org/W3102944959","https://openalex.org/W3173622057","https://openalex.org/W3176550827","https://openalex.org/W3183953540","https://openalex.org/W3198024709","https://openalex.org/W4206064074","https://openalex.org/W4231287357","https://openalex.org/W4236226996","https://openalex.org/W4236656499","https://openalex.org/W4241858315","https://openalex.org/W6675727724"],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W650102067","https://openalex.org/W4206577045","https://openalex.org/W3086237447","https://openalex.org/W1550806730","https://openalex.org/W2589740103","https://openalex.org/W2172084996","https://openalex.org/W1501284171","https://openalex.org/W3033055359","https://openalex.org/W1966967794"],"abstract_inverted_index":{"Cardinality":[0],"estimation":[1,200],"is":[2,175,233],"one":[3,225],"of":[4,26,59],"the":[5,24,27,47,78,81,90,130,159,192,229,237],"most":[6],"fundamental":[7],"and":[8,56,106,135,174,180,206],"challenging":[9],"problems":[10],"in":[11,103,241],"query":[12,119,155,230],"optimization.":[13],"Neither":[14],"classical":[15,82],"nor":[16],"learning-based":[17,91,142,195],"methods":[18,92],"yield":[19],"satisfactory":[20],"performance":[21],"when":[22],"estimating":[23,73],"cardinality":[25,39,239],"join":[28,74,118],"queries.":[29,62,75],"They":[30],"either":[31],"rely":[32],"on":[33,165],"simplified":[34],"assumptions":[35],"leading":[36,51],"to":[37,45,52,85,93,133,148,157,178,227,236],"ineffective":[38],"estimates":[40,190],"or":[41,152,213],"build":[42],"large":[43],"models":[44],"understand":[46],"complicated":[48],"data":[49],"distributions,":[50],"long":[53],"planning":[54],"times":[55],"a":[57,68,104,117,125,170],"lack":[58],"generalizability":[60],"across":[61],"In":[63,182,216],"this":[64],"paper,":[65],"we":[66],"propose":[67],"new":[69],"framework":[70],"FactorJoin":[71,76,99,121,144,168,185,218],"for":[72],"combines":[77],"idea":[79],"behind":[80],"join-histogram":[83],"method":[84],"efficiently":[86,136],"handle":[87],"joins":[88,150],"with":[89,197],"accurately":[94],"capture":[95],"attribute":[96],"correlation":[97],"Specifically,":[98],"scans":[100],"every":[101],"table":[102],"DB":[105],"builds":[107],"single-table":[108,166],"conditional":[109],"distributions":[110,132],"during":[111],"an":[112],"offline":[113],"preparation":[114],"phase.":[115],"When":[116],"comes,":[120],"translates":[122],"it":[123,162],"into":[124],"factor":[126],"graph":[127],"model":[128,204],"over":[129],"learned":[131],"effectively":[134],"estimate":[137,220],"its":[138],"cardinality.":[139],"Unlike":[140],"existing":[141],"methods,":[143,196],"does":[145],"not":[146],"need":[147],"de-normalize":[149],"upfront":[151],"require":[153],"executed":[154],"workloads":[156],"train":[158,179],"model.":[160],"Since":[161],"only":[163],"relies":[164],"statistics,":[167],"has":[169],"small":[171],"space":[172],"overhead":[173],"extremely":[176],"easy":[177],"maintain.":[181],"our":[183],"evaluation,":[184],"can":[186,219],"produce":[187],"more":[188],"effective":[189],"than":[191],"previous":[193],"state-of-the-art":[194],"40x":[198],"less":[199],"latency,":[201],"100x":[202,207],"smaller":[203],"size,":[205],"faster":[208],"training":[209],"speed":[210],"at":[211],"comparable":[212],"better":[214],"accuracy.":[215],"addition,":[217],"10,000":[221],"sub-plan":[222],"queries":[223],"within":[224],"second":[226],"optimize":[228],"plan,":[231],"which":[232],"very":[234],"close":[235],"traditional":[238],"estimators":[240],"commercial":[242],"DBMS.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}