{"id":"https://openalex.org/W4380433147","doi":"https://doi.org/10.1145/3588940","title":"Making It Tractable to Catch Duplicates and Conflicts in Graphs","display_name":"Making It Tractable to Catch Duplicates and Conflicts in Graphs","publication_year":2023,"publication_date":"2023-05-26","ids":{"openalex":"https://openalex.org/W4380433147","doi":"https://doi.org/10.1145/3588940"},"language":"en","primary_location":{"id":"doi:10.1145/3588940","doi":"https://doi.org/10.1145/3588940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588940","pdf_url":null,"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,"listed_in":["cwts-core","norway-1","vabb-shw"],"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"},"volume":null,"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/A5070565287","display_name":"Wenfei Fan","orcid":"https://orcid.org/0000-0001-5149-2656","observed_orcids":["https://orcid.org/0000-0001-5149-2656"]},"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"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wenfei Fan","raw_affiliation_strings":["Shenzhen Institute of Computing Sciences; University of Edinburgh; & Beihang University, Shenzhen, China","& Beihang University, Shenzhen, China","University of Edinburgh"],"raw_orcid":"https://orcid.org/0000-0001-5149-2656","affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Computing Sciences; University of Edinburgh; & Beihang University, Shenzhen, China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I98677209"]},{"raw_affiliation_string":"& Beihang University, Shenzhen, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088474186","display_name":"W. Fu","orcid":"https://orcid.org/0009-0008-2799-4865","observed_orcids":["https://orcid.org/0009-0008-2799-4865"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenzhi Fu","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0008-2799-4865","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102723856","display_name":"Ruochun Jin","orcid":"https://orcid.org/0009-0001-2763-0577","observed_orcids":["https://orcid.org/0009-0001-2763-0577","https://orcid.org/0000-0001-6217-4223"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruochun Jin","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0001-2763-0577","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042814502","display_name":"Muyang Liu","orcid":"https://orcid.org/0009-0005-8267-7748","observed_orcids":["https://orcid.org/0009-0005-8267-7748"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Muyang Liu","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-8267-7748","affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013499387","display_name":"Ping L\u00fc","orcid":"https://orcid.org/0000-0003-4919-8989","observed_orcids":["https://orcid.org/0000-0003-4919-8989"]},"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":"Ping Lu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4919-8989","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100675047","display_name":"Chao Tian","orcid":"https://orcid.org/0000-0002-9670-367X","observed_orcids":["https://orcid.org/0000-0002-9670-367X"]},"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":"Chao Tian","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9670-367X","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8445,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85475005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9761000275611877,"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":0.9761000275611877,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.016499999910593033,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.002099999925121665,"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/entity-resolution","display_name":"entity resolution","score":0.878000020980835},{"id":"https://openalex.org/keywords/conflict-resolution","display_name":"conflict resolution","score":0.9800000190734863},{"id":"https://openalex.org/keywords/satisfiability","display_name":"satisfiability","score":0.5839999914169312},{"id":"https://openalex.org/keywords/implication","display_name":"implication","score":0.7160000205039978},{"id":"https://openalex.org/keywords/validation","display_name":"validation","score":0.45399999618530273},{"id":"https://openalex.org/keywords/star-patterns","display_name":"star patterns","score":0.5839999914169312},{"id":"https://openalex.org/keywords/error-detection","display_name":"error detection","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045769691467285},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5516343712806702},{"id":"https://openalex.org/C134026603","wikidata":"https://www.wikidata.org/wiki/Q846354","display_name":"P","level":3,"score":0.4802301526069641},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4732784926891327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34846195578575134},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3316621780395508}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3588940","doi":"https://doi.org/10.1145/3588940","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3588940","pdf_url":null,"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,"listed_in":["cwts-core","norway-1","vabb-shw"],"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":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1733809484","display_name":null,"funder_award_id":"SKLSDE-2021ZX-11","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"},{"id":"https://openalex.org/G3276400090","display_name":"EPSRC Centre for Doctoral Training in Pervasive Parallelism","funder_award_id":"EP/L01503X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5276589493","display_name":null,"funder_award_id":"61602023","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"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":"https://ror.org/017r4dj03"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W163762105","https://openalex.org/W254113056","https://openalex.org/W1181317657","https://openalex.org/W1571341547","https://openalex.org/W1734573275","https://openalex.org/W1862165198","https://openalex.org/W1977041160","https://openalex.org/W1977379542","https://openalex.org/W1981590391","https://openalex.org/W1986017822","https://openalex.org/W2000437271","https://openalex.org/W2011039300","https://openalex.org/W2022166150","https://openalex.org/W2024443169","https://openalex.org/W2026147624","https://openalex.org/W2042387478","https://openalex.org/W2059554611","https://openalex.org/W2077518845","https://openalex.org/W2102297485","https://openalex.org/W2113607096","https://openalex.org/W2114887670","https://openalex.org/W2119320829","https://openalex.org/W2122255072","https://openalex.org/W2133409729","https://openalex.org/W2136663836","https://openalex.org/W2151502664","https://openalex.org/W2164625277","https://openalex.org/W2166549982","https://openalex.org/W2169940602","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2210838531","https://openalex.org/W2271319393","https://openalex.org/W2425348221","https://openalex.org/W2439326083","https://openalex.org/W2492590231","https://openalex.org/W2523329595","https://openalex.org/W2569536984","https://openalex.org/W2579319185","https://openalex.org/W2591700809","https://openalex.org/W2767324389","https://openalex.org/W2767518867","https://openalex.org/W2767681556","https://openalex.org/W2772675153","https://openalex.org/W2775696413","https://openalex.org/W2788919350","https://openalex.org/W2791055742","https://openalex.org/W2794573079","https://openalex.org/W2798649495","https://openalex.org/W2805602976","https://openalex.org/W2875652255","https://openalex.org/W2914111272","https://openalex.org/W2915915402","https://openalex.org/W2929941791","https://openalex.org/W2942740455","https://openalex.org/W2970641574","https://openalex.org/W2997756720","https://openalex.org/W3000214033","https://openalex.org/W3002269711","https://openalex.org/W3011807731","https://openalex.org/W3031504748","https://openalex.org/W3038423637","https://openalex.org/W3040722616","https://openalex.org/W3041128325","https://openalex.org/W3043426275","https://openalex.org/W3082965822","https://openalex.org/W3102173443","https://openalex.org/W3164439293","https://openalex.org/W4205204813","https://openalex.org/W4211032081","https://openalex.org/W4246012463","https://openalex.org/W4283329289","https://openalex.org/W4283372881","https://openalex.org/W4285602153","https://openalex.org/W4288057690"],"related_works":["https://openalex.org/W4404006790","https://openalex.org/W6978136196","https://openalex.org/W4408734722","https://openalex.org/W2925156238","https://openalex.org/W4226124724","https://openalex.org/W107201577","https://openalex.org/W2164618618","https://openalex.org/W4232329126","https://openalex.org/W2487678730","https://openalex.org/W4403791808"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3],"approach":[4],"for":[5,91,102,127],"entity":[6],"resolution":[7,11],"(ER)":[8],"and":[9,36,65,82,120,122,130,154,163],"conflict":[10],"(CR)":[12],"in":[13,87],"large-scale":[14],"graphs.":[15],"It":[16],"is":[17],"based":[18],"on":[19],"a":[20,54,69,108,123],"class":[21],"of":[22,31,62,68,98,118],"Graph":[23],"Cleaning":[24],"Rules":[25],"(GCRs),":[26],"which":[27],"support":[28],"the":[29,74,79,96,116,135],"primitives":[30],"relational":[32],"data":[33],"cleaning":[34],"rules,":[35,49],"may":[37],"embed":[38],"machine":[39],"learning":[40],"classifiers":[41],"as":[42,93],"predicates.":[43],"As":[44],"opposed":[45,94],"to":[46,58,72,95,111,144],"previous":[47,103,173],"graph":[48,56,104,174],"GCRs":[50,113,167],"are":[51,85,150,168],"defined":[52],"with":[53,166,172,176],"dual":[55],"pattern":[57],"accommodate":[59],"irregular":[60],"structures":[61],"schemaless":[63],"graphs,":[64,156],"adopt":[66],"patterns":[67,119],"star":[70],"form":[71],"reduce":[73,145],"complexity.":[75],"We":[76,106,138],"show":[77,139],"that":[78,140,160],"satisfiability,":[80],"implication":[81],"validation":[83],"problems":[84,101],"all":[86],"polynomial":[88],"time":[89],"(PTIME)":[90],"GCRs,":[92],"intractability":[97],"these":[99,141],"classical":[100],"dependencies.":[105],"develop":[107],"parallel":[109,124],"algorithm":[110,126],"discover":[112],"by":[114,132],"combining":[115],"generations":[117],"predicates,":[121],"PTIME":[125],"\"deep\"":[128],"ER":[129],"CR":[131],"recursively":[133],"applying":[134],"mined":[136],"GCRs.":[137],"algorithms":[142],"guarantee":[143],"runtime":[146],"when":[147],"more":[148],"processors":[149],"used.":[151],"Using":[152],"real-life":[153],"synthetic":[155],"we":[157],"experimentally":[158],"verify":[159],"rule":[161],"discovery":[162],"error":[164],"detection":[165],"substantially":[169],"faster":[170],"than":[171],"dependencies,":[175],"improved":[177],"accuracy.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-06-14T00:00:00"}