{"id":"https://openalex.org/W3034413451","doi":"https://doi.org/10.24963/ijcai.2020/301","title":"Decorrelated Clustering with Data Selection Bias","display_name":"Decorrelated Clustering with Data Selection Bias","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3034413451","doi":"https://doi.org/10.24963/ijcai.2020/301","mag":"3034413451"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2020/301","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/301","pdf_url":"https://www.ijcai.org/proceedings/2020/0301.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2020/0301.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100411469","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0002-4444-7811"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028965727","display_name":"Shaohua Fan","orcid":"https://orcid.org/0000-0002-1224-4243"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohua Fan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041727387","display_name":"Kun Kuang","orcid":"https://orcid.org/0000-0001-7024-9790"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Kuang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705849","display_name":"Chuan Shi","orcid":"https://orcid.org/0000-0002-3734-0266"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Shi","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107933120","display_name":"Jiawei Liu","orcid":"https://orcid.org/0000-0002-6100-4000"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Liu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100608154","display_name":"Bai Wang","orcid":"https://orcid.org/0009-0007-4592-795X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bai Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100411469"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.9814,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78163702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2177","last_page":"2183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10057","display_name":"Face and Expression Recognition","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9948999881744385,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9937999844551086,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8605399131774902},{"id":"https://openalex.org/keywords/decorrelation","display_name":"Decorrelation","score":0.8383053541183472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6604084968566895},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6321663856506348},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5380930304527283},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5185085535049438},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.5001235008239746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44081738591194153},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4364601969718933},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4330631494522095},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3251578211784363},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3065062165260315},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22246170043945312},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1766975224018097}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8605399131774902},{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.8383053541183472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604084968566895},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6321663856506348},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5380930304527283},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5185085535049438},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.5001235008239746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44081738591194153},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4364601969718933},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4330631494522095},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3251578211784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3065062165260315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22246170043945312},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1766975224018097}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2020/301","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/301","pdf_url":"https://www.ijcai.org/proceedings/2020/0301.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2020/301","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2020/301","pdf_url":"https://www.ijcai.org/proceedings/2020/0301.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1352607027","display_name":null,"funder_award_id":"2018YFB1402600","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2702356746","display_name":null,"funder_award_id":"61702","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3133715941","display_name":null,"funder_award_id":"U1936220","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3200522107","display_name":null,"funder_award_id":"61702296","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3551653136","display_name":null,"funder_award_id":"2018AAA0101900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4957550077","display_name":null,"funder_award_id":"61772082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4962807355","display_name":null,"funder_award_id":"U1936220","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5620609558","display_name":null,"funder_award_id":"U1936104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5689994630","display_name":null,"funder_award_id":"No. 2018AAA0101900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6010275601","display_name":null,"funder_award_id":"B14026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G630077093","display_name":null,"funder_award_id":"No. 2018","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6687479257","display_name":null,"funder_award_id":"U1936220","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7750549614","display_name":null,"funder_award_id":"201912","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8118681200","display_name":null,"funder_award_id":"2018YFB1402600","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913074851","display_name":null,"funder_award_id":"61806020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034413451.pdf","grobid_xml":"https://content.openalex.org/works/W3034413451.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W120692785","https://openalex.org/W1576597967","https://openalex.org/W1677409904","https://openalex.org/W1977556410","https://openalex.org/W2057266281","https://openalex.org/W2073161435","https://openalex.org/W2112483442","https://openalex.org/W2132914434","https://openalex.org/W2139122730","https://openalex.org/W2149466042","https://openalex.org/W2168345951","https://openalex.org/W2627183927","https://openalex.org/W2740813652","https://openalex.org/W2807006342","https://openalex.org/W2807992610","https://openalex.org/W2885707361","https://openalex.org/W2908166511","https://openalex.org/W2997746169","https://openalex.org/W3012918605","https://openalex.org/W4289542433","https://openalex.org/W4293568472","https://openalex.org/W4295126650"],"related_works":["https://openalex.org/W1999117613","https://openalex.org/W2040929534","https://openalex.org/W3022637481","https://openalex.org/W2393816671","https://openalex.org/W3120229345","https://openalex.org/W2111119584","https://openalex.org/W3144143113","https://openalex.org/W3039964395","https://openalex.org/W2804957450","https://openalex.org/W2357208913"],"abstract_inverted_index":{"Most":[0],"of":[1,44,98,167],"existing":[2],"clustering":[3,45,79],"algorithms":[4],"are":[5,96,115],"proposed":[6],"without":[7,130],"considering":[8],"the":[9,22,30,42,85,91,100,112,121,126,137,143,165],"selection":[10,56,82,174],"bias":[11,27,57,175],"in":[12,145],"data.":[13],"In":[14,66],"many":[15],"real":[16,151],"applications,":[17],"however,":[18],"one":[19],"cannot":[20],"guarantee":[21],"data":[23,81,128],"is":[24,58],"unbiased.":[25],"Selection":[26],"might":[28],"bring":[29],"unexpected":[31,38,52,107,131,169],"correlation":[32,132],"between":[33],"features":[34],"and":[35],"ignoring":[36],"those":[37,51],"correlations":[39,53,108,171],"will":[40],"hurt":[41],"performance":[43,162],"algorithms.":[46],"Therefore,":[47],"how":[48],"to":[49,89,105,140],"remove":[50,106],"induced":[54,172],"by":[55,173],"extremely":[59],"important":[60],"yet":[61],"largely":[62],"unexplored":[63],"for":[64,78],"clustering.":[65,177],"this":[67],"paper,":[68],"we":[69,135],"propose":[70],"a":[71],"novel":[72],"Decorrelation":[73],"regularized":[74],"K-Means":[75],"algorithm":[76,159],"(DCKM)":[77],"with":[80,117],"bias.":[83],"Specifically,":[84],"decorrelation":[86],"regularizer":[87],"aims":[88],"learn":[90],"global":[92],"sample":[93,101],"weights":[94,114],"which":[95,119],"capable":[97],"balancing":[99],"distribution,":[102],"so":[103],"as":[104],"among":[109],"features.":[110],"Meanwhile,":[111],"learned":[113],"combined":[116],"k-means,":[118],"makes":[120],"reweighted":[122],"k-means":[123],"cluster":[124],"on":[125,150],"inherent":[127],"distribution":[129],"influence.":[133],"Moreover,":[134],"derive":[136],"updating":[138],"rules":[139],"effectively":[141],"infer":[142],"parameters":[144],"DCKM.":[146],"Extensive":[147],"experiments":[148],"results":[149],"world":[152],"datasets":[153],"well":[154],"demonstrate":[155],"that":[156],"our":[157],"DCKM":[158],"achieves":[160],"significant":[161],"gains,":[163],"indicating":[164],"necessity":[166],"removing":[168],"feature":[170],"when":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}