{"id":"https://openalex.org/W4403577492","doi":"https://doi.org/10.1145/3627673.3679226","title":"GARF: A Self-supervised Data Cleaning System with SeqGAN","display_name":"GARF: A Self-supervised Data Cleaning System with SeqGAN","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403577492","doi":"https://doi.org/10.1145/3627673.3679226"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-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 University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0005-6443-6692","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hanghai Cui","orcid":"https://orcid.org/0009-0005-1474-6377"},"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":"Hanghai Cui","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0005-1474-6377","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 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 University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-0310-6372","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 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 University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-5307-4893","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, 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 University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0002-0166-1324","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tianlong Guo","orcid":"https://orcid.org/0000-0003-3608-1810"},"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":"Tianlong Guo","raw_affiliation_strings":["Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0003-3608-1810","affiliations":[{"raw_affiliation_string":"Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21134307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5260","last_page":"5264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9940000176429749,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9848999977111816,"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/computer-science","display_name":"Computer science","score":0.6646888852119446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3790914714336395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6646888852119446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3790914714336395}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3679226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2063103859","https://openalex.org/W2078132546","https://openalex.org/W2153531471","https://openalex.org/W2167333415","https://openalex.org/W2262592273","https://openalex.org/W2544486974","https://openalex.org/W3000214033","https://openalex.org/W3197847098","https://openalex.org/W3210636622","https://openalex.org/W4317767732"],"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":{"High-quality":[0],"data":[1,5,14,27,35,44,55,75,93,99,123,135,154,177],"is":[2,92,157],"essential":[3],"for":[4,51,62,126],"science":[6],"and":[7,26,114,134,151,165,172],"machine":[8,64,120],"learning":[9,65],"applications,":[10],"but":[11],"unfortunately,":[12],"real-world":[13,180],"often":[15],"contains":[16],"significant":[17],"amounts":[18],"of":[19],"errors,":[20],"such":[21],"as":[22,168],"typos,":[23],"missing":[24],"values,":[25],"inconsistencies.":[28],"Despite":[29],"all":[30],"the":[31,111,116],"efforts":[32],"in":[33,42,179],"cleaning":[34,45,76,178],"using":[36],"either":[37,52],"logical":[38],"or":[39,58],"learning-based":[40],"methods,":[41],"practice,":[43],"still":[46],"requires":[47],"high":[48],"human":[49],"cost,":[50],"manually":[53],"providing":[54],"repairing":[56],"rules":[57,101,125,133,150],"preparing":[59],"labeled":[60],"datasets":[61],"training":[63],"models.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"introduce":[71],"GARF,":[72],"a":[73,107,143],"novel":[74],"system":[77],"based":[78],"on":[79,176],"sequence":[80],"generative":[81],"adversarial":[82],"networks":[83],"(SeqGAN).":[84],"One":[85],"key":[86],"information":[87,117],"GARF":[88,105,141,167],"tries":[89],"to":[90,109,121,146],"learn":[91],"repair":[94,100,124,152],"rules.":[95,161],"To":[96],"automatically":[97],"extracts":[98],"from":[102],"dirty":[103,153],"data,":[104],"employs":[106],"SeqGAN":[108],"capture":[110],"dependency":[112],"relationships,":[113],"converts":[115],"learned":[118],"by":[119],"interpretable":[122],"humans.":[127],"Additionally,":[128],"considering":[129],"that":[130],"both":[131],"generated":[132],"may":[136],"not":[137],"be":[138],"fully":[139],"trusted,":[140],"provides":[142],"co-cleaning":[144],"process":[145],"iteratively":[147],"update":[148],"inaccurate":[149],"until":[155],"there":[156],"no":[158],"tuple":[159],"violating":[160],"We":[162],"have":[163],"implemented":[164],"deployed":[166],"an":[169],"open-sourced":[170],"system,":[171],"demonstrated":[173],"its":[174],"usability":[175],"scenarios.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}