{"id":"https://openalex.org/W4413978617","doi":"https://doi.org/10.14778/3749646.3749681","title":"UniClean: A Scalable Data Cleaning Solution for Mixed Errors Based on Unified Cleaners and Optimized Cleaning Workflow","display_name":"UniClean: A Scalable Data Cleaning Solution for Mixed Errors Based on Unified Cleaners and Optimized Cleaning Workflow","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4413978617","doi":"https://doi.org/10.14778/3749646.3749681"},"language":"en","primary_location":{"id":"doi:10.14778/3749646.3749681","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3749646.3749681","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/A5035726597","display_name":"Xiaoou Ding","orcid":"https://orcid.org/0000-0002-9426-1820"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Ding","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zekai Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekai Qian","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396644","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-4097-8703"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Wang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762805","display_name":"Siying Chen","orcid":"https://orcid.org/0000-0002-2708-6559"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siying Chen","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112750887","display_name":"Yafeng Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Tang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102660855","display_name":"Hongbin Su","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Su","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873903","display_name":"Huan Hu","orcid":"https://orcid.org/0000-0003-0119-5789"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Hu","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337643","display_name":"Chen Wang","orcid":"https://orcid.org/0000-0003-0204-2362"},"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":"Chen Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3194,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83908831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"11","first_page":"4117","last_page":"4130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9873999953269958,"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":0.9822999835014343,"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/workflow","display_name":"Workflow","score":0.8279155492782593},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6920850276947021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6129417419433594},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.46176499128341675},{"id":"https://openalex.org/keywords/process-engineering","display_name":"Process engineering","score":0.43175873160362244},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3415016531944275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1852560043334961}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8279155492782593},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6920850276947021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6129417419433594},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.46176499128341675},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.43175873160362244},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3415016531944275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1852560043334961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3749646.3749681","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3749646.3749681","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":50,"referenced_works":["https://openalex.org/W1593947693","https://openalex.org/W1964786778","https://openalex.org/W1976732638","https://openalex.org/W2018490621","https://openalex.org/W2021651899","https://openalex.org/W2041442195","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2049058890","https://openalex.org/W2089206172","https://openalex.org/W2130887504","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2190899134","https://openalex.org/W2544486974","https://openalex.org/W2549035799","https://openalex.org/W2591700809","https://openalex.org/W2598425513","https://openalex.org/W2929941791","https://openalex.org/W2948145720","https://openalex.org/W2970651950","https://openalex.org/W3005822199","https://openalex.org/W3011807731","https://openalex.org/W3013134982","https://openalex.org/W3014705052","https://openalex.org/W3023664246","https://openalex.org/W3082197983","https://openalex.org/W3085684300","https://openalex.org/W3123375411","https://openalex.org/W3173352120","https://openalex.org/W3175358996","https://openalex.org/W3176502563","https://openalex.org/W3196442060","https://openalex.org/W3197847098","https://openalex.org/W4206031975","https://openalex.org/W4211029301","https://openalex.org/W4289533948","https://openalex.org/W4298468057","https://openalex.org/W4313131509","https://openalex.org/W4385270437","https://openalex.org/W4400909535","https://openalex.org/W4400909959","https://openalex.org/W4400909995","https://openalex.org/W4401353630","https://openalex.org/W4402043009","https://openalex.org/W4404181119","https://openalex.org/W4407695089","https://openalex.org/W4412340925","https://openalex.org/W6966844147"],"related_works":["https://openalex.org/W1981780420","https://openalex.org/W2182707996","https://openalex.org/W45233828","https://openalex.org/W2964988449","https://openalex.org/W2397952901","https://openalex.org/W2029380707","https://openalex.org/W188202134","https://openalex.org/W4255934811","https://openalex.org/W2465382974","https://openalex.org/W2010229520"],"abstract_inverted_index":{"Data":[0],"cleaning":[1,18,22,48,65,74,83,87,93,147,165],"is":[2],"an":[3,91],"essential":[4],"technique":[5],"to":[6,42,67,72,80,95,144],"enhance":[7],"data":[8,34],"quality.":[9],"Despite":[10],"the":[11,45,164],"proposal":[12],"of":[13,27,105,172],"various":[14,70],"algorithms":[15],"with":[16,32,50],"different":[17],"strategies,":[19],"current":[20],"automated":[21],"technologies":[23],"still":[24],"fall":[25],"short":[26],"practical":[28],"requirements":[29],"when":[30],"dealing":[31],"large-scale":[33,130],"containing":[35],"mixed":[36,46,98],"errors.":[37,99],"This":[38],"paper":[39],"presents":[40],"UniClean":[41,100,135],"efficiently":[43],"solve":[44],"error":[47,109,121],"problem":[49],"three":[51],"key":[52],"technical":[53],"contributions.":[54],"(1)":[55],"A":[56,86],"unified":[57],"construction":[58],"and":[59,129,149,157],"extension":[60],"method":[61],"for":[62,170],"cleaners,":[63],"enabling":[64],"methods":[66],"easily":[68],"utilize":[69],"cleaners":[71],"perform":[73],"tasks.":[75],"(2)":[76],"Three":[77],"optimization":[78],"strategies":[79],"achieve":[81],"efficiency-oriented":[82],"preparation.":[84],"(3)":[85],"algorithm":[88],"based":[89],"on":[90,127,159],"optimized":[92],"process":[94,166],"effectively":[96],"clean":[97],"achieves":[101,136],"a":[102],"time":[103],"complexity":[104],"O":[106],"(|":[107],"D":[108,120],"|":[110,113,115,119],"4":[111],"\u00b7":[112,118],"Op":[114],"+":[116],"|D|":[117],"|),":[122],"significantly":[123],"enhancing":[124],"scalability.":[125],"Experiments":[126],"public":[128],"enterprise":[131],"datasets":[132],"demonstrate":[133],"that":[134],"over":[137],"40%":[138],"improvement":[139],"across":[140],"five":[141,145],"metrics,":[142],"compared":[143],"state-of-the-art":[146],"methods,":[148],"delivers":[150],"more":[151],"than":[152],"30%":[153],"gains":[154],"in":[155],"F1":[156],"REDR":[158],"complex":[160],"datasets,":[161],"while":[162],"completing":[163],"within":[167],"hours":[168],"even":[169],"millions":[171],"records.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}