{"id":"https://openalex.org/W4413349890","doi":"https://doi.org/10.1109/icde65448.2025.00362","title":"UniClean: A Multi-Signal Fusion Pipeline for Optimizing Data Cleaning Workflow","display_name":"UniClean: A Multi-Signal Fusion Pipeline for Optimizing Data Cleaning Workflow","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413349890","doi":"https://doi.org/10.1109/icde65448.2025.00362"},"language":"en","primary_location":{"id":"doi:10.1109/icde65448.2025.00362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde65448.2025.00362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 41st International Conference on Data Engineering (ICDE)","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/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":true,"raw_author_name":"Xiaoou Ding","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396652","display_name":"Hongzhi Wang","orcid":"https://orcid.org/0000-0002-7521-2871"},"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":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005858991","display_name":"Zhe Sun","orcid":"https://orcid.org/0000-0002-9664-9749"},"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":"Zhe Sun","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, 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":["School of Computer Science and Technology, Harbin Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101873903","display_name":"Huan Hu","orcid":"https://orcid.org/0000-0003-0119-5789"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huan Hu","raw_affiliation_strings":["Huawei Cloud Computing Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud Computing Technologies Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5035726597"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.9093,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87907356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4600","last_page":"4603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9241999983787537,"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":0.9241999983787537,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7701016068458557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7162219285964966},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7111808061599731},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5366342663764954},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.522331178188324},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.459628701210022},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23715782165527344},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18484309315681458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.143654465675354},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09403333067893982}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7701016068458557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7162219285964966},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7111808061599731},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5366342663764954},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.522331178188324},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.459628701210022},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23715782165527344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18484309315681458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.143654465675354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09403333067893982},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde65448.2025.00362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde65448.2025.00362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 41st International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2591700809","https://openalex.org/W3023664246","https://openalex.org/W3028760276","https://openalex.org/W3082197983","https://openalex.org/W3173352120","https://openalex.org/W3176502563","https://openalex.org/W4381329328","https://openalex.org/W4400909995","https://openalex.org/W4401353630","https://openalex.org/W4404181119"],"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/W2132659060","https://openalex.org/W2031992971","https://openalex.org/W3214791684","https://openalex.org/W2152662039"],"abstract_inverted_index":{"Data":[0],"quality":[1],"issues":[2],"are":[3],"prevalent":[4],"in":[5,50,155],"information":[6,174],"systems,":[7],"making":[8],"data":[9,53,69,79,94,126,154,170],"cleaning":[10,28,39,62,85,95,100,105,113,130,138,171],"a":[11,83,99,104,110],"complex":[12],"and":[13,20,41,109,116,125,141],"time-consuming":[14],"task,":[15],"particularly":[16],"with":[17],"large-scale":[18],"datasets":[19],"the":[21,36,42,57,66,73,93,119,149,166],"lack":[22,31],"of":[23,38,44,68,168],"standardized":[24],"automated":[25,32],"processes.":[26],"Existing":[27],"pipelines":[29],"often":[30],"schemes":[33],"to":[34,91,128,147],"guide":[35],"execution":[37],"algorithms":[40],"sequence":[43],"error":[45],"corrections,":[46],"limiting":[47],"their":[48],"practicality":[49],"real-world":[51],"big":[52,78,169],"applications.":[54],"To":[55],"address":[56],"growing":[58],"demand":[59],"for":[60,76,112,152],"advanced":[61],"tools":[63],"driven":[64],"by":[65],"complexity":[67],"activities,":[70],"we":[71],"propose":[72],"UniClean":[74,81,133,163],"framework":[75],"on-demand":[77],"cleaning.":[80],"employs":[82],"unified":[84],"operation":[86,131],"(Uniop)":[87],"from":[88,122],"multiple":[89],"cleaners":[90],"optimize":[92],"workflow.":[96],"It":[97],"integrates":[98],"parameter":[101,106],"generation":[102],"pipeline,":[103,108],"selection":[107],"module":[111],"process":[114],"preparation":[115,127],"optimization,":[117],"covering":[118],"entire":[120],"workflow":[121,139],"cleaner":[123],"modeling":[124],"optimal":[129],"generation.":[132],"provides":[134],"an":[135],"adaptive":[136],"(data-driven":[137],"generation)":[140],"flexible":[142],"(multi-signal":[143],"extension":[144],"system)":[145],"solution":[146],"meet":[148],"urgent":[150],"need":[151],"high-quality":[153],"today's":[156],"data-driven":[157],"decision-making":[158],"environments.":[159],"We":[160],"demonstrate":[161],"how":[162],"effectively":[164],"addresses":[165],"challenges":[167],"across":[172],"diverse":[173],"system":[175],"landscapes.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}