{"id":"https://openalex.org/W4402043009","doi":"https://doi.org/10.14778/3681954.3682015","title":"DAFDiscover: Robust Mining Algorithm for Dynamic Approximate Functional Dependencies on Dirty Data","display_name":"DAFDiscover: Robust Mining Algorithm for Dynamic Approximate Functional Dependencies on Dirty Data","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402043009","doi":"https://doi.org/10.14778/3681954.3682015"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3682015","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682015","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/A5035726597","display_name":"Xiaoou Ding","orcid":"https://orcid.org/0000-0002-9426-1820"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoou Ding","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113357767","display_name":"Yixing Lu","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixing Lu","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396644","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-4097-8703"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100337643","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0204-2362"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018096615","display_name":"Yida Liu","orcid":"https://orcid.org/0000-0003-3169-5506"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yida Liu","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100373520","display_name":"Jianmin Wang","orcid":"https://orcid.org/0000-0001-8703-8973"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Wang","raw_affiliation_strings":["Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5035726597"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.8213,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86247035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"17","issue":"11","first_page":"3484","last_page":"3496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6985646486282349},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696677029132843},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6584711074829102},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.6164612770080566},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5196905732154846},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.49036312103271484},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46364298462867737},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43879082798957825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23456192016601562},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08315584063529968},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.07539403438568115}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6985646486282349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696677029132843},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6584711074829102},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.6164612770080566},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5196905732154846},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.49036312103271484},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46364298462867737},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43879082798957825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23456192016601562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08315584063529968},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.07539403438568115},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3681954.3682015","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3682015","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1502954553","https://openalex.org/W1537955876","https://openalex.org/W1569990199","https://openalex.org/W1571341547","https://openalex.org/W1967167578","https://openalex.org/W2024443169","https://openalex.org/W2029570660","https://openalex.org/W2102489964","https://openalex.org/W2156026066","https://openalex.org/W2166549982","https://openalex.org/W2186686397","https://openalex.org/W2190899134","https://openalex.org/W2439326083","https://openalex.org/W2481159763","https://openalex.org/W2532748481","https://openalex.org/W2618188015","https://openalex.org/W2798658665","https://openalex.org/W2891500072","https://openalex.org/W2952207484","https://openalex.org/W2995343792","https://openalex.org/W2998531464","https://openalex.org/W2998944545","https://openalex.org/W3031504748","https://openalex.org/W3080831182","https://openalex.org/W3116285643","https://openalex.org/W4211029301","https://openalex.org/W4320030233","https://openalex.org/W4385270308","https://openalex.org/W4400909535","https://openalex.org/W4400909995","https://openalex.org/W6888945715","https://openalex.org/W6907748762","https://openalex.org/W6926303013","https://openalex.org/W6926399812","https://openalex.org/W6926450783","https://openalex.org/W6945421096","https://openalex.org/W6945436263","https://openalex.org/W6964138771","https://openalex.org/W6964248249"],"related_works":["https://openalex.org/W2392606101","https://openalex.org/W3162070149","https://openalex.org/W2072918301","https://openalex.org/W2133756937","https://openalex.org/W2385315033","https://openalex.org/W2384822125","https://openalex.org/W2362842011","https://openalex.org/W1839867872","https://openalex.org/W1845544376","https://openalex.org/W3149145737"],"abstract_inverted_index":{"Data":[0],"dependency":[1],"mining":[2,77,93,147],"plays":[3],"a":[4,49,61,105,116],"crucial":[5],"role":[6],"in":[7,41,44],"understanding":[8],"data":[9],"relationships.":[10],"To":[11],"address":[12],"the":[13,85,132,138],"increasing":[14],"complexities":[15],"of":[16,90,135,140],"real-world":[17],"data,":[18],"Approximate":[19],"Functional":[20],"Dependencies":[21],"(AFDs)":[22],"have":[23],"been":[24],"introduced,":[25],"building":[26],"upon":[27],"traditional":[28],"FD.":[29],"However,":[30],"existing":[31,144],"AFD":[32,51,92,146],"approaches":[33],"use":[34],"static":[35],"relaxation":[36],"coefficients,":[37],"limiting":[38],"their":[39],"effectiveness":[40,139],"capturing":[42],"dependencies":[43,78],"noisy":[45,81],"data.":[46,82,124],"We":[47,59,99],"propose":[48],"dynamic":[50],"variant,":[52],"DAFD,":[53],"which":[54],"incorporates":[55],"attribute":[56],"error":[57],"rates.":[58],"establish":[60],"bijection":[62],"between":[63],"DAFD":[64,109,136],"and":[65,71,87,114,137],"FD,":[66],"develop":[67],"its":[68,102],"inference":[69],"system,":[70],"introduce":[72],"DAFDiscover,":[73],"an":[74],"algorithm":[75],"for":[76,107,119],"directly":[79],"on":[80,122,127],"DAFDiscover":[83,141],"matches":[84],"time":[86],"space":[88],"complexity":[89],"SOTA":[91,145],"methods":[94],"while":[95],"offering":[96],"superior":[97],"performance.":[98],"theoretically":[100],"prove":[101],"correctness,":[103],"provide":[104],"method":[106],"calculating":[108],"probabilities":[110],"(DAFD-":[111],"prob":[112],"),":[113],"derive":[115],"lower":[117],"bound":[118],"DAFD's":[120],"validity":[121],"dirty":[123],"Experimental":[125],"results":[126],"multiple":[128],"public":[129],"datasets":[130],"demonstrate":[131],"semantic":[133],"superiority":[134],"compared":[142],"to":[143],"techniques.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-05-12T08:28:47.272897","created_date":"2025-10-10T00:00:00"}