{"id":"https://openalex.org/W4381786100","doi":"https://doi.org/10.1109/tkde.2023.3288209","title":"Efficient Discovery of Functional Dependencies on Massive Data","display_name":"Efficient Discovery of Functional Dependencies on Massive Data","publication_year":2023,"publication_date":"2023-06-23","ids":{"openalex":"https://openalex.org/W4381786100","doi":"https://doi.org/10.1109/tkde.2023.3288209"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2023.3288209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3288209","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5085267247","display_name":"Xiaolong Wan","orcid":"https://orcid.org/0000-0003-4502-085X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Wan","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0003-4502-085X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006689000","display_name":"Xixian Han","orcid":"https://orcid.org/0000-0001-5477-9249"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixian Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0001-5477-9249","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044022943","display_name":"Jinbao Wang","orcid":"https://orcid.org/0000-0003-1430-3179"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinbao Wang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0003-1430-3179","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100387065","display_name":"Jianzhong Li","orcid":"https://orcid.org/0000-0002-4119-0571"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhong Li","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"raw_orcid":"https://orcid.org/0000-0002-4119-0571","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5525,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8305727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"36","issue":"1","first_page":"107","last_page":"121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9936000108718872,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9894000291824341,"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":0.8438271284103394},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.8434906005859375},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7112255096435547},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.6759580373764038},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.5338481664657593},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.5089926719665527},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.49333205819129944},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.452421098947525},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.431151419878006},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3862060308456421},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.138953298330307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09089544415473938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8438271284103394},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.8434906005859375},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7112255096435547},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.6759580373764038},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5338481664657593},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.5089926719665527},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.49333205819129944},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.452421098947525},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.431151419878006},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3862060308456421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.138953298330307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09089544415473938},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2023.3288209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2023.3288209","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1083341597","display_name":null,"funder_award_id":"U21A20513","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1498996750","https://openalex.org/W1502954553","https://openalex.org/W1512840853","https://openalex.org/W1569403765","https://openalex.org/W1571341547","https://openalex.org/W1870305865","https://openalex.org/W1881756506","https://openalex.org/W1977119497","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2044108498","https://openalex.org/W2117546628","https://openalex.org/W2128476487","https://openalex.org/W2159328231","https://openalex.org/W2166549982","https://openalex.org/W2266772167","https://openalex.org/W2287926972","https://openalex.org/W2439326083","https://openalex.org/W2803396353","https://openalex.org/W2952207484","https://openalex.org/W3139384714","https://openalex.org/W3145004415","https://openalex.org/W3150565720","https://openalex.org/W3171487259","https://openalex.org/W4289646359","https://openalex.org/W6639586388","https://openalex.org/W6697044326","https://openalex.org/W6736299510"],"related_works":["https://openalex.org/W1968137129","https://openalex.org/W2125223317","https://openalex.org/W2177745035","https://openalex.org/W4232172855","https://openalex.org/W2168592511","https://openalex.org/W4242762735","https://openalex.org/W4245631587","https://openalex.org/W2116767780","https://openalex.org/W165346131","https://openalex.org/W1594511838"],"abstract_inverted_index":{"Functional":[0],"dependencies":[1,79,119,156,180],"are":[2,27],"the":[3,8,31,42,100,116,122,130,153,158],"most":[4],"common":[5],"constraints":[6],"in":[7,20,38,56,160],"design":[9],"theory":[10],"for":[11,103],"relational":[12],"databases,":[13],"which":[14,51,98],"have":[15],"very":[16],"important":[17],"practical":[18],"applications":[19],"many":[21],"areas.":[22],"Different":[23],"kinds":[24],"of":[25,86,95,145],"algorithms":[26,44],"proposed":[28],"to":[29,59,76,128,142],"discover":[30,178],"functional":[32,78,118,155,179],"dependencies.":[33],"However,":[34],"it":[35],"is":[36,74,140],"found":[37],"this":[39,68],"paper":[40],"that":[41,175],"existing":[43],"cannot":[45,52],"deal":[46],"well":[47],"with":[48,105],"massive":[49,81,182],"data":[50,172,183],"be":[53],"held":[54],"entirely":[55],"memory":[57,61],"due":[58],"high":[60,64],"consumption":[62],"and":[63,120,170],"computation":[65],"cost.":[66],"In":[67,111,148],"paper,":[69],"a":[70,90],"novel":[71],"algorithm":[72],"FSC":[73,87,114,151,176],"presented":[75],"compute":[77],"on":[80,89,168,181],"data.":[82],"The":[83,135,163],"two-step":[84],"execution":[85],"relies":[88],"pre-computed":[91],"update-friendly":[92],"assistant":[93],"structure":[94],"comparable":[96,126],"pairs":[97,102,127],"reflect":[99],"identifier":[101],"tuples":[104],"at":[106],"least":[107],"one":[108],"equal":[109],"attribute.":[110],"step":[112,149,161],"1,":[113],"determines":[115],"violated":[117],"introduces":[121],"selective":[123],"comparison":[124,133],"by":[125,157],"reduce":[129],"required":[131,154],"pairwise":[132],"significantly.":[134],"direct":[136],"value-combination":[137],"compression":[138],"strategy":[139],"devised":[141],"process":[143],"attributes":[144],"small":[146],"cardinality.":[147],"2,":[150],"induces":[152],"results":[159],"1.":[162],"extensive":[164],"experimental":[165],"results,":[166],"conducted":[167],"synthetic":[169],"real-life":[171],"sets,":[173],"show":[174],"can":[177],"efficiently.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}