{"id":"https://openalex.org/W4317767732","doi":"https://doi.org/10.14778/3570690.3570694","title":"Self-Supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks","display_name":"Self-Supervised and Interpretable Data Cleaning with Sequence Generative Adversarial Networks","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4317767732","doi":"https://doi.org/10.14778/3570690.3570694"},"language":"en","primary_location":{"id":"doi:10.14778/3570690.3570694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3570690.3570694","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/A5102812417","display_name":"Jinfeng Peng","orcid":"https://orcid.org/0009-0005-6443-6692"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinfeng Peng","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015251362","display_name":"Derong Shen","orcid":"https://orcid.org/0000-0003-0310-6372"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Derong Shen","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HKBU, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKBU, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056818995","display_name":"Tieying Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieying Liu","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026995541","display_name":"Yue Kou","orcid":"https://orcid.org/0000-0002-5307-4893"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Kou","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102979521","display_name":"Tiezheng Nie","orcid":"https://orcid.org/0000-0002-0166-1324"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiezheng Nie","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008379334","display_name":"Hang Cui","orcid":"https://orcid.org/0000-0003-3762-4645"},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Hang Cui","raw_affiliation_strings":["UIUC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072406974","display_name":"Ge Yu","orcid":"https://orcid.org/0000-0002-3171-8889"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge Yu","raw_affiliation_strings":["Northeastern Univ., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern Univ., China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6359,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.91341595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"3","first_page":"433","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9977999925613403,"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/T11363","display_name":"Dental Radiography and Imaging","score":0.9538999795913696,"subfield":{"id":"https://openalex.org/subfields/3504","display_name":"Oral Surgery"},"field":{"id":"https://openalex.org/fields/35","display_name":"Dentistry"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8325352668762207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7579495906829834},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.7387520670890808},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.703568696975708},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5737773180007935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5573129057884216},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.544718861579895},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5363095998764038},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.521282434463501},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.44562917947769165},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42323917150497437},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41008198261260986},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1443258821964264}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8325352668762207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579495906829834},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.7387520670890808},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.703568696975708},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5737773180007935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5573129057884216},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.544718861579895},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5363095998764038},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.521282434463501},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.44562917947769165},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42323917150497437},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41008198261260986},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1443258821964264},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3570690.3570694","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3570690.3570694","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":[{"display_name":"Reduced inequalities","score":0.550000011920929,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1573646728","https://openalex.org/W2008271340","https://openalex.org/W2019891208","https://openalex.org/W2023052779","https://openalex.org/W2045054164","https://openalex.org/W2046298800","https://openalex.org/W2063103859","https://openalex.org/W2078501237","https://openalex.org/W2089206172","https://openalex.org/W2113607096","https://openalex.org/W2137775416","https://openalex.org/W2153531471","https://openalex.org/W2166549982","https://openalex.org/W2167333415","https://openalex.org/W2169940602","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2183774130","https://openalex.org/W2262592273","https://openalex.org/W2266772167","https://openalex.org/W2295468252","https://openalex.org/W2544486974","https://openalex.org/W2560674852","https://openalex.org/W2591700809","https://openalex.org/W2615796676","https://openalex.org/W2726342193","https://openalex.org/W2804988694","https://openalex.org/W2889005129","https://openalex.org/W2948145720","https://openalex.org/W2982763192","https://openalex.org/W2995343792","https://openalex.org/W3000214033","https://openalex.org/W3004034804","https://openalex.org/W3034942164","https://openalex.org/W3082197983","https://openalex.org/W3165814564","https://openalex.org/W3197847098","https://openalex.org/W4213245422","https://openalex.org/W4297970464","https://openalex.org/W6680599078","https://openalex.org/W6739878388"],"related_works":["https://openalex.org/W3005996785","https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4328029048","https://openalex.org/W2952936466","https://openalex.org/W2914998939","https://openalex.org/W2561036008","https://openalex.org/W2554314924","https://openalex.org/W4288624664","https://openalex.org/W2809882560"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,51,56,79,92,101,133,143,185],"problem":[3],"of":[4,66,145,153,187],"self-supervised":[5],"and":[6,70,117,148,156,167,174,181],"interpretable":[7,13],"data":[8,14,45,109,163,193],"cleaning,":[9],"which":[10,159],"automatically":[11],"extracts":[12],"repair":[15,46,110],"rules":[16,47,147],"from":[17,123,201],"dirty":[18,124,162,202],"data.":[19,125,149,176],"In":[20],"this":[21,128],"paper,":[22],"we":[23],"propose":[24],"a":[25,63,67,71,86],"novel":[26],"framework,":[27],"namely":[28],"Garf,":[29],"based":[30],"on":[31,179],"sequence":[32],"generative":[33],"adversarial":[34],"networks":[35],"(SeqGAN).":[36],"One":[37],"key":[38],"information":[39],"Garf":[40,61,130,150,189],"tries":[41],"to":[42,77,107,140],"capture":[43],"is":[44,53],"(for":[48],"example,":[49],"if":[50],"city":[52,87],"\"Dothan\",":[54],"then":[55],"county":[57,93],"should":[58],"be":[59,95,105],"\"Houston\").":[60,98],"employs":[62],"SeqGAN":[64],"consisting":[65],"generator":[68,102],"G":[69,76,103],"discriminator":[72,138],"D":[73],"that":[74],"trains":[75],"learn":[78],"dependency":[80],"relationships":[81,135],"(":[82],"e.g.":[83],",":[84],"given":[85],"value":[88],"\"Dothan\"":[89],"as":[90,97],"input,":[91],"can":[94,104],"determined":[96],"After":[99],"training,":[100],"used":[106],"generate":[108],"rules,":[111,119],"but":[112],"may":[113],"contain":[114],"both":[115,146,154],"trusted":[116],"untrusted":[118],"especially":[120],"when":[121],"learning":[122,200],"To":[126],"mitigate":[127],"problem,":[129],"further":[131],"updates":[132],"learned":[134],"with":[136,164,196],"another":[137],"D'":[139],"iteratively":[141],"improve":[142],"quality":[144],"takes":[151],"advantages":[152],"logical":[155],"learning-based":[157],"methods,":[158],"allow":[160],"cleaning":[161,194],"high":[165,197],"interpretability":[166],"have":[168],"no":[169],"requirements":[170],"for":[171],"prior":[172],"knowledge":[173],"training":[175],"Extensive":[177],"experiments":[178],"real-world":[180],"synthetic":[182],"datasets":[183,203],"demonstrate":[184],"effectiveness":[186],"Garf.":[188],"achieves":[190],"new":[191],"state-of-the-art":[192],"result":[195],"accuracy,":[198],"through":[199],"without":[204],"human":[205],"supervision.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}