{"id":"https://openalex.org/W4410538818","doi":"https://doi.org/10.14778/3717755.3717777","title":"Discovering Approximate Inclusion Dependencies","display_name":"Discovering Approximate Inclusion Dependencies","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4410538818","doi":"https://doi.org/10.14778/3717755.3717777"},"language":"en","primary_location":{"id":"doi:10.14778/3717755.3717777","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3717755.3717777","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/A5039957758","display_name":"Qiushi Su","orcid":"https://orcid.org/0009-0001-8494-2913"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdong Su","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101627769","display_name":"Zhikang Wang","orcid":"https://orcid.org/0000-0001-9587-1965"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikang Wang","raw_affiliation_strings":["School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005944481","display_name":"Zijing Tan","orcid":"https://orcid.org/0000-0001-6332-780X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijing Tan","raw_affiliation_strings":["School of Computer Science, Fudan University, China and Shanghai Key Laboratory of Data Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, China and Shanghai Key Laboratory of Data Science","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006980420","display_name":"Shuai Ma","orcid":"https://orcid.org/0000-0002-4050-0443"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Ma","raw_affiliation_strings":["SKLSDE Lab, Beihang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKLSDE Lab, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3057,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59722296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"18","issue":"4","first_page":"1210","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9986000061035156,"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":0.9986000061035156,"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/T11719","display_name":"Data Quality and Management","score":0.9983999729156494,"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":0.9983000159263611,"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/inclusion","display_name":"Inclusion (mineral)","score":0.6841080188751221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4614950120449066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36493757367134094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1545441448688507}],"concepts":[{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.6841080188751221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4614950120449066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36493757367134094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1545441448688507},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3717755.3717777","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3717755.3717777","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":40,"referenced_works":["https://openalex.org/W1819449330","https://openalex.org/W1981578383","https://openalex.org/W2020230082","https://openalex.org/W2067494918","https://openalex.org/W2096461223","https://openalex.org/W2099637074","https://openalex.org/W2099725016","https://openalex.org/W2106039833","https://openalex.org/W2108790711","https://openalex.org/W2125552274","https://openalex.org/W2140313762","https://openalex.org/W2159186077","https://openalex.org/W2162294668","https://openalex.org/W2182148130","https://openalex.org/W2232417456","https://openalex.org/W2287134858","https://openalex.org/W2476695476","https://openalex.org/W2623129571","https://openalex.org/W2741470040","https://openalex.org/W2798658665","https://openalex.org/W2811353042","https://openalex.org/W2885500131","https://openalex.org/W2896385696","https://openalex.org/W2963174348","https://openalex.org/W2970727798","https://openalex.org/W2988782038","https://openalex.org/W2997756720","https://openalex.org/W3046745582","https://openalex.org/W3139384714","https://openalex.org/W3171487259","https://openalex.org/W3174637548","https://openalex.org/W3174731955","https://openalex.org/W3215037963","https://openalex.org/W4206031975","https://openalex.org/W4283383705","https://openalex.org/W4312628841","https://openalex.org/W4321448337","https://openalex.org/W4360986132","https://openalex.org/W4380433179","https://openalex.org/W6717843792"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"Inclusion":[0],"dependencies":[1],"(INDs)":[2],"are":[3],"widely":[4],"used":[5],"in":[6,26,81],"data":[7,30],"management":[8],"tasks.":[9],"The":[10,109],"discovery":[11,53,92,183,202],"techniques":[12,113,147],"of":[13,20,38,54,75,106,213],"INDs":[14,24,56,61],"have":[15],"thus":[16],"received":[17],"a":[18,48,66,72,141],"lot":[19],"attention,":[21],"for":[22,181],"discovering":[23],"valid":[25,157],"data.":[27],"However,":[28],"real-world":[29],"quality":[31],"issues":[32],"may":[33],"lead":[34],"to":[35,46,59,83,100,114,127],"partial":[36],"violations":[37,130],"INDs.":[39],"This":[40,69],"paper":[41,70],"makes":[42],"the":[43,52,84,138,172,174,188],"first":[44],"effort":[45],"provide":[47,197],"comprehensive":[49],"study":[50],"on":[51,78,88,104,132,185],"approximate":[55],"(AINDs),":[57],"aiming":[58],"identify":[60,101,156],"with":[62,124,191,207],"error":[63],"rates":[64],"below":[65],"given":[67],"threshold.":[68],"introduces":[71],"new":[73],"definition":[74,86],"AIND":[76,129,182,189],"based":[77,87,103,131,184],"deletion":[79,194],"semantics,":[80,187],"addition":[82],"existing":[85,179],"insertion":[89,186,192],"semantics.":[90,108],"A":[91],"method":[93,110,139,176,203],"is":[94],"developed":[95],"that":[96,117,148],"can":[97,149,196,204],"be":[98],"configured":[99],"AINDs":[102,154,158],"either":[105],"these":[107],"combines":[111],"partitioning":[112],"handle":[115],"tables":[116],"cannot":[118],"all":[119,162],"fit":[120],"into":[121],"memory":[122],"simultaneously,":[123],"novel":[125,142],"approaches":[126],"quantify":[128],"partitioned":[133],"tables.":[134],"To":[135],"improve":[136],"efficiency,":[137],"employs":[140],"three-layer":[143],"filtering":[144],"structure":[145],"and":[146,155,170,193,200],"potentially":[150],"prune":[151],"invalid":[152],"candidate":[153],"without":[159],"necessarily":[160],"processing":[161],"tuples.":[163],"We":[164],"conduct":[165],"an":[166],"extensive":[167],"experimental":[168],"evaluation":[169],"verify":[171],"following:":[173],"proposed":[175],"significantly":[177],"outperforms":[178],"methods":[180],"discoveries":[190],"semantics":[195],"complementary":[198],"results,":[199],"our":[201],"effectively":[205],"deal":[206],"dirty":[208],"dataset":[209],"containing":[210],"various":[211],"types":[212],"errors.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}