{"id":"https://openalex.org/W4283206275","doi":"https://doi.org/10.1145/3534678.3539232","title":"Learning Fair Representation via Distributional Contrastive Disentanglement","display_name":"Learning Fair Representation via Distributional Contrastive Disentanglement","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4283206275","doi":"https://doi.org/10.1145/3534678.3539232"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539232","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5003650851","display_name":"Changdae Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Changdae Oh","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025347774","display_name":"Heeji Won","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Heeji Won","raw_affiliation_strings":["Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032614836","display_name":"Junhyuk So","orcid":"https://orcid.org/0000-0002-9210-1284"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Junhyuk So","raw_affiliation_strings":["POSTECH, Pohang, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"POSTECH, Pohang, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015937857","display_name":"Taero Kim","orcid":"https://orcid.org/0000-0003-2377-2241"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taero Kim","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700697","display_name":"Yewon Kim","orcid":"https://orcid.org/0000-0003-1902-6262"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yewon Kim","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029968461","display_name":"Hosik Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hosik Choi","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025711483","display_name":"Kyungwoo Song","orcid":"https://orcid.org/0000-0003-0082-4280"},"institutions":[{"id":"https://openalex.org/I124633538","display_name":"University of Seoul","ror":"https://ror.org/05en5nh73","country_code":"KR","type":"education","lineage":["https://openalex.org/I124633538"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyungwoo Song","raw_affiliation_strings":["University of Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"University of Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I124633538"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5003650851"],"corresponding_institution_ids":["https://openalex.org/I124633538"],"apc_list":null,"apc_paid":null,"fwci":2.8266,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92319924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1295","last_page":"1305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994000196456909,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9732999801635742,"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/debiasing","display_name":"Debiasing","score":0.7827796936035156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7382487654685974},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7301080226898193},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6706474423408508},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6006413698196411},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5971837639808655},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5606602430343628},{"id":"https://openalex.org/keywords/swap","display_name":"Swap (finance)","score":0.5231928825378418},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4776398241519928},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4723340570926666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32147812843322754},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.20775824785232544}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.7827796936035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382487654685974},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7301080226898193},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6706474423408508},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6006413698196411},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5971837639808655},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5606602430343628},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.5231928825378418},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4776398241519928},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4723340570926666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32147812843322754},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.20775824785232544},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539232","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539232","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137},{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G8595924568","display_name":null,"funder_award_id":"021R1F1A1060117","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2732026016","https://openalex.org/W2753738274","https://openalex.org/W2963116854","https://openalex.org/W2963394878","https://openalex.org/W2997310315","https://openalex.org/W3092425680","https://openalex.org/W3097489012","https://openalex.org/W3110081891","https://openalex.org/W3153872861","https://openalex.org/W3203690435","https://openalex.org/W4300011764","https://openalex.org/W7016021835"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"Learning":[0],"fair":[1],"representation":[2,18],"is":[3],"crucial":[4],"for":[5,135],"achieving":[6],"fairness":[7,45],"or":[8],"debiasing":[9],"sensitive":[10,72,85,102],"information.":[11],"Most":[12],"existing":[13],"works":[14],"rely":[15],"on":[16,158],"adversarial":[17,27],"learning":[19,28,138],"to":[20,32,68,98,104,149],"inject":[21],"some":[22],"invariance":[23],"into":[24,71],"representation.":[25,49],"However,":[26],"methods":[29],"are":[30],"known":[31],"suffer":[33],"from":[34,107,113,167],"relatively":[35],"unstable":[36],"training,":[37],"and":[38,46,73,110,132,163,173],"this":[39],"might":[40],"harm":[41],"the":[42,65,79,89,114,151],"balance":[43],"between":[44],"predictiveness":[47],"of":[48,81,126],"We":[50,76,121],"propose":[51],"a":[52,123,145],"new":[53,124,146],"approach,":[54],"learningFAir":[55],"Representation":[56],"via":[57],"distributional":[58,136],"CONtrastive":[59],"Variational":[60],"AutoEncoder":[61],"(FarconVAE),":[62],"which":[63],"induces":[64],"latent":[66,97,116],"space":[67],"be":[69,99,105],"disentangled":[70],"non-sensitive":[74,96,115],"parts.":[75],"first":[77],"construct":[78],"pair":[80],"observations":[82],"with":[83,88,139],"different":[84],"attributes":[86],"but":[87],"same":[90],"labels.":[91],"Then,":[92],"FarconVAE":[93,154],"enforces":[94],"each":[95,108],"closer,":[100],"while":[101],"latents":[103],"far":[106,112],"other":[109],"also":[111],"by":[117,130],"contrasting":[118],"their":[119],"distributions.":[120],"provide":[122],"type":[125],"contrastive":[127,137],"loss":[128,148],"motivated":[129],"Gaussian":[131],"Student-t":[133],"kernels":[134],"theoretical":[140],"analysis.":[141],"Besides,":[142],"we":[143],"adopt":[144],"swap-reconstruction":[147],"boost":[150],"disentanglement":[152],"further.":[153],"shows":[155],"superior":[156],"performance":[157],"fairness,":[159],"pretrained":[160],"model":[161],"debiasing,":[162],"domain":[164],"generalization":[165],"tasks":[166],"various":[168],"modalities,":[169],"including":[170],"tabular,":[171],"image,":[172],"text.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}