{"id":"https://openalex.org/W4405616836","doi":"https://doi.org/10.1007/s41019-024-00266-7","title":"Relational Data Cleaning Meets Artificial Intelligence: A Survey","display_name":"Relational Data Cleaning Meets Artificial Intelligence: A Survey","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W4405616836","doi":"https://doi.org/10.1007/s41019-024-00266-7"},"language":"en","primary_location":{"id":"doi:10.1007/s41019-024-00266-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-024-00266-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-024-00266-7.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s41019-024-00266-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101599455","display_name":"Jingyu Zhu","orcid":"https://orcid.org/0009-0009-1611-7717"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Zhu","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012758615","display_name":"Xintong Zhao","orcid":"https://orcid.org/0000-0003-1867-804X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xintong Zhao","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734399","display_name":"Yu Sun","orcid":"https://orcid.org/0009-0007-7398-2972"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Sun","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0007-7398-2972","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084430029","display_name":"Shaoxu Song","orcid":"https://orcid.org/0000-0002-9503-2755"},"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":"Shaoxu Song","raw_affiliation_strings":["School of Software, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062064974","display_name":"Xiaojie Yuan","orcid":"https://orcid.org/0000-0002-5876-6856"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojie Yuan","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100734399"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":3.6464,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93974694,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"10","issue":"2","first_page":"147","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9860000014305115,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8003145456314087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47527188062667847},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40996018052101135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003145456314087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47527188062667847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40996018052101135}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41019-024-00266-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-024-00266-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-024-00266-7.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fcbe7fff44974b7e92b949215b03030e","is_oa":false,"landing_page_url":"https://doaj.org/article/fcbe7fff44974b7e92b949215b03030e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science and Engineering, Vol 10, Iss 2, Pp 147-174 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s41019-024-00266-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41019-024-00266-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41019-024-00266-7.pdf","source":{"id":"https://openalex.org/S2486411021","display_name":"Data Science and Engineering","issn_l":"2364-1185","issn":["2364-1185","2364-1541"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G2021969373","display_name":null,"funder_award_id":"92267203","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G212106316","display_name":null,"funder_award_id":"72342017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2154614518","display_name":"\u65f6\u5e8f\u6570\u636e\u6e05\u7406\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072265","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G320219132","display_name":null,"funder_award_id":"62302241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4667360632","display_name":null,"funder_award_id":"62372252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4671081833","display_name":null,"funder_award_id":"22JCQNJC01520","funder_id":"https://openalex.org/F4320323993","funder_display_name":"Natural Science Foundation of Tianjin City"},{"id":"https://openalex.org/G7091651887","display_name":null,"funder_award_id":"62021002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7508556822","display_name":null,"funder_award_id":"62232005","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/F4320323021","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75"},{"id":"https://openalex.org/F4320323993","display_name":"Natural Science Foundation of Tianjin City","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405616836.pdf"},"referenced_works_count":154,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1502001434","https://openalex.org/W1502624642","https://openalex.org/W1519775745","https://openalex.org/W1530232915","https://openalex.org/W1567694985","https://openalex.org/W1583837637","https://openalex.org/W1598553907","https://openalex.org/W1966836840","https://openalex.org/W1975388904","https://openalex.org/W1976364950","https://openalex.org/W1976413982","https://openalex.org/W1976732638","https://openalex.org/W1977185509","https://openalex.org/W1977908705","https://openalex.org/W1985258161","https://openalex.org/W1986332411","https://openalex.org/W1988904801","https://openalex.org/W1991299759","https://openalex.org/W1991635626","https://openalex.org/W1992479406","https://openalex.org/W2000613518","https://openalex.org/W2002928429","https://openalex.org/W2008271340","https://openalex.org/W2011764809","https://openalex.org/W2021355462","https://openalex.org/W2032441932","https://openalex.org/W2041442195","https://openalex.org/W2043246077","https://openalex.org/W2044469685","https://openalex.org/W2045240677","https://openalex.org/W2047337966","https://openalex.org/W2050767557","https://openalex.org/W2055621992","https://openalex.org/W2056081083","https://openalex.org/W2064186732","https://openalex.org/W2066046820","https://openalex.org/W2079229132","https://openalex.org/W2089206172","https://openalex.org/W2096863518","https://openalex.org/W2097295325","https://openalex.org/W2100358124","https://openalex.org/W2111104102","https://openalex.org/W2114933215","https://openalex.org/W2128372630","https://openalex.org/W2134843796","https://openalex.org/W2142472956","https://openalex.org/W2146332392","https://openalex.org/W2146944094","https://openalex.org/W2147805208","https://openalex.org/W2156502664","https://openalex.org/W2163874082","https://openalex.org/W2164187405","https://openalex.org/W2165336231","https://openalex.org/W2166597282","https://openalex.org/W2167546040","https://openalex.org/W2168512593","https://openalex.org/W2170604454","https://openalex.org/W2170712852","https://openalex.org/W2171118759","https://openalex.org/W2183774130","https://openalex.org/W2191264216","https://openalex.org/W2295247008","https://openalex.org/W2296719434","https://openalex.org/W2394811972","https://openalex.org/W2437617937","https://openalex.org/W2517120592","https://openalex.org/W2548122763","https://openalex.org/W2574666645","https://openalex.org/W2591700809","https://openalex.org/W2604928999","https://openalex.org/W2605029335","https://openalex.org/W2615796676","https://openalex.org/W2618188015","https://openalex.org/W2621614835","https://openalex.org/W2726858467","https://openalex.org/W2735252542","https://openalex.org/W2748435103","https://openalex.org/W2786361040","https://openalex.org/W2798323405","https://openalex.org/W2807955733","https://openalex.org/W2808833850","https://openalex.org/W2875652255","https://openalex.org/W2894914645","https://openalex.org/W2897574832","https://openalex.org/W2901288224","https://openalex.org/W2902085258","https://openalex.org/W2904287913","https://openalex.org/W2914436728","https://openalex.org/W2914585587","https://openalex.org/W2921009679","https://openalex.org/W2929941791","https://openalex.org/W2932702699","https://openalex.org/W2943955885","https://openalex.org/W2948145720","https://openalex.org/W2949032458","https://openalex.org/W2949848919","https://openalex.org/W2951565755","https://openalex.org/W2951837249","https://openalex.org/W2953231542","https://openalex.org/W2955443275","https://openalex.org/W2962959301","https://openalex.org/W2976683998","https://openalex.org/W2987471611","https://openalex.org/W3005551496","https://openalex.org/W3005822199","https://openalex.org/W3022460540","https://openalex.org/W3023664246","https://openalex.org/W3030026364","https://openalex.org/W3030764521","https://openalex.org/W3031359560","https://openalex.org/W3034856749","https://openalex.org/W3080402700","https://openalex.org/W3082197983","https://openalex.org/W3091123787","https://openalex.org/W3094251544","https://openalex.org/W3098198535","https://openalex.org/W3098337560","https://openalex.org/W3098444442","https://openalex.org/W3100646146","https://openalex.org/W3102208177","https://openalex.org/W3105977086","https://openalex.org/W3128430136","https://openalex.org/W3147796863","https://openalex.org/W3157286898","https://openalex.org/W3158303960","https://openalex.org/W3159275022","https://openalex.org/W3165814564","https://openalex.org/W3174290263","https://openalex.org/W3174526319","https://openalex.org/W3176502563","https://openalex.org/W3186875255","https://openalex.org/W3188751135","https://openalex.org/W3197847098","https://openalex.org/W3207970821","https://openalex.org/W3210748167","https://openalex.org/W4206662295","https://openalex.org/W4239448463","https://openalex.org/W4247105055","https://openalex.org/W4251911433","https://openalex.org/W4281753537","https://openalex.org/W4281826654","https://openalex.org/W4295808856","https://openalex.org/W4300187280","https://openalex.org/W4317767732","https://openalex.org/W4321448364","https://openalex.org/W4321786857","https://openalex.org/W4384159544","https://openalex.org/W4388620358","https://openalex.org/W4390723615","https://openalex.org/W4402041885","https://openalex.org/W4404407645","https://openalex.org/W6605918897","https://openalex.org/W6630595383"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Abstract":[0],"Relational":[1],"data":[2,35,71,131,134,190],"play":[3],"a":[4],"crucial":[5],"role":[6],"in":[7,189],"various":[8,83],"fields,":[9],"but":[10],"they":[11],"are":[12,100,112],"often":[13],"plagued":[14],"by":[15],"low-quality":[16],"issues":[17,186],"such":[18],"as":[19,102,114],"erroneous":[20],"and":[21,43,51,133,153,166,175,184,192],"missing":[22],"values,":[23],"which":[24],"can":[25],"terribly":[26],"impact":[27],"downstream":[28],"applications.":[29],"To":[30],"tackle":[31],"these":[32],"issues,":[33],"relational":[34,138],"cleaning":[36,72,80,87,137,191],"with":[37,49],"traditional":[38,147],"signals,":[39,81],"e.g.,":[40],"statistics,":[41],"constraints,":[42],"clusters,":[44],"have":[45,66],"been":[46,67],"extensively":[47],"studied,":[48],"interpretability":[50],"efficiency.":[52],"Recently,":[53],"considering":[54],"the":[55,70,86,143,182],"strong":[56],"capability":[57],"of":[58,157],"modeling":[59],"complex":[60],"relationships,":[61],"artificial":[62],"intelligence":[63],"(AI)":[64],"techniques":[65,84],"introduced":[68],"into":[69,85,171],"field.":[73],"These":[74],"AI-based":[75],"methods":[76,95,145,158],"either":[77],"consider":[78],"multiple":[79],"integrate":[82],"system,":[88],"or":[89,148],"incorporate":[90],"neural":[91,98],"networks.":[92],"Among":[93],"them,":[94],"utilizing":[96],"deep":[97,103],"networks":[99],"classified":[101,113],"learning":[104,116],"(DL)":[105],"based,":[106],"while":[107],"those":[108],"that":[109],"do":[110],"not":[111],"machine":[115],"(ML)":[117],"based.":[118],"In":[119],"this":[120],"study,":[121],"we":[122,168,180],"focus":[123],"on":[124],"three":[125],"essential":[126],"tasks":[127],"(i.e.,":[128],"error":[129],"detection,":[130],"repairing,":[132],"imputation)":[135],"for":[136,196],"data,":[139],"to":[140],"comprehensively":[141],"review":[142],"representative":[144],"using":[146],"AI":[149],"techniques.":[150],"By":[151],"comparing":[152],"analyzing":[154],"two":[155],"types":[156],"across":[159],"five":[160],"dimensions":[161],"(cost,":[162],"generalization,":[163],"interpretability,":[164],"efficiency,":[165],"effectiveness),":[167],"provide":[169],"insights":[170],"their":[172],"strengths,":[173],"weaknesses,":[174],"suitable":[176],"application":[177],"scenarios.":[178],"Finally,":[179],"analyze":[181],"challenges":[183],"open":[185],"currently":[187],"faced":[188],"discuss":[193],"possible":[194],"directions":[195],"future":[197],"studies.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}