{"id":"https://openalex.org/W3133655632","doi":"https://doi.org/10.48550/arxiv.2103.04243","title":"Estimating and Improving Fairness with Adversarial Learning","display_name":"Estimating and Improving Fairness with Adversarial Learning","publication_year":2021,"publication_date":"2021-03-07","ids":{"openalex":"https://openalex.org/W3133655632","doi":"https://doi.org/10.48550/arxiv.2103.04243","mag":"3133655632"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2103.04243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04243","pdf_url":"https://arxiv.org/pdf/2103.04243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.04243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100458657","display_name":"Xiaoxiao Li","orcid":"https://orcid.org/0000-0002-8833-0244","observed_orcids":["https://orcid.org/0000-0002-8833-0244"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Xiaoxiao","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035551115","display_name":"Ziteng Cui","orcid":"https://orcid.org/0000-0002-6126-2712","observed_orcids":["https://orcid.org/0000-0002-6126-2712"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Ziteng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020044791","display_name":"Yifan Wu","orcid":"https://orcid.org/0000-0002-2856-9835","observed_orcids":["https://orcid.org/0000-0002-2856-9835"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Yifan","raw_affiliation_strings":["#N#               * University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#               * University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gu, Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210110652","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gu, Lin","raw_affiliation_strings":["Riken"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Riken","institution_ids":["https://openalex.org/I4210110652"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042711470","display_name":"Tatsuya Harada","orcid":"https://orcid.org/0000-0002-3712-3691","observed_orcids":["https://orcid.org/0000-0002-3712-3691"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Harada, Tatsuya","raw_affiliation_strings":["Univ.\\ of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ.\\ of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8901000022888184,"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"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.8901000022888184,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.032099999487400055,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.01769999973475933,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.9369999766349792},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.7350000143051147},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.777999997138977},{"id":"https://openalex.org/keywords/bias-mitigation","display_name":"bias mitigation","score":0.6869999766349792},{"id":"https://openalex.org/keywords/bias-detection","display_name":"bias detection","score":0.8059999942779541},{"id":"https://openalex.org/keywords/orthogonality-regularization","display_name":"orthogonality regularization","score":0.925000011920929},{"id":"https://openalex.org/keywords/skin-lesion-classification","display_name":"skin lesion classification","score":0.7929999828338623},{"id":"https://openalex.org/keywords/medical-image-analysis","display_name":"medical image analysis","score":0.7670000195503235},{"id":"https://openalex.org/keywords/sensitive-attributes","display_name":"sensitive attributes","score":0.6299999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734248161315918},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6931334733963013},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6490461230278015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6353132724761963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5811113119125366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5281161069869995},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42844778299331665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42122745513916016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1189737319946289},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2103.04243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04243","pdf_url":"https://arxiv.org/pdf/2103.04243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2103.04243","doi":"https://doi.org/10.48550/arxiv.2103.04243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.04243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.04243","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04243","pdf_url":"https://arxiv.org/pdf/2103.04243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.8974000215530396,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2100960835","https://openalex.org/W2124635032","https://openalex.org/W2173520492","https://openalex.org/W2346705140","https://openalex.org/W2725155646","https://openalex.org/W2784397426","https://openalex.org/W2892246301","https://openalex.org/W2895471314","https://openalex.org/W2951576127","https://openalex.org/W2963290659","https://openalex.org/W2963349562","https://openalex.org/W2990751682","https://openalex.org/W2996490626","https://openalex.org/W3007679811","https://openalex.org/W3015826434","https://openalex.org/W3019370719","https://openalex.org/W3026980374","https://openalex.org/W3030030520","https://openalex.org/W3035447285","https://openalex.org/W3043469766","https://openalex.org/W3091268787","https://openalex.org/W3100844313","https://openalex.org/W3102785203"],"related_works":["https://openalex.org/W4404573377","https://openalex.org/W4412950278","https://openalex.org/W4387397186","https://openalex.org/W4387583834","https://openalex.org/W7111561838","https://openalex.org/W4410249949","https://openalex.org/W7116601719","https://openalex.org/W4406495577","https://openalex.org/W4405528443","https://openalex.org/W4312349151"],"abstract_inverted_index":{"Fairness":[0],"and":[1,40,61,101,134,191],"accountability":[2],"are":[3,137],"two":[4,82],"essential":[5],"pillars":[6],"for":[7,157,189],"trustworthy":[8],"Artificial":[9],"Intelligence":[10],"(AI)":[11],"in":[12,22,43,194],"healthcare.":[13],"However,":[14],"the":[15,44,69,81,110,117,120,150,158,183,195],"existing":[16],"AI":[17],"model":[18],"may":[19],"be":[20,85],"biased":[21],"its":[23],"decision":[24],"marking.":[25],"To":[26],"tackle":[27],"this":[28,113],"issue,":[29],"we":[30,52,90],"propose":[31,53],"an":[32,76],"adversarial":[33,114],"multi-task":[34],"training":[35,115],"strategy":[36],"to":[37,54,79,84,126,146],"simultaneously":[38],"mitigate":[39],"detect":[41],"bias":[42,60,127],"deep":[45,94,196],"learning-based":[46,197],"medical":[47,198],"image":[48,199],"analysis":[49,200],"system.":[50,201],"Specifically,":[51],"add":[55],"a":[56,62,106,140,169],"discrimination":[57],"module":[58,64,152],"against":[59],"critical":[63,151],"that":[65,142],"predicts":[66],"unfairness":[67],"within":[68],"base":[70],"classification":[71],"model.":[72],"We":[73,164],"further":[74],"impose":[75],"orthogonality":[77],"regularization":[78],"force":[80],"modules":[83],"independent":[86],"during":[87],"training.":[88],"Hence,":[89],"can":[91,153],"keep":[92],"these":[93,147],"learning":[95],"tasks":[96],"distinct":[97],"from":[98,119],"one":[99],"another,":[100],"avoid":[102],"collapsing":[103],"them":[104],"into":[105,139],"singular":[107],"point":[108],"on":[109,168],"manifold.":[111],"Through":[112],"method,":[116],"data":[118,159],"underprivileged":[121],"group,":[122],"which":[123],"is":[124,143],"vulnerable":[125],"because":[128],"of":[129,185],"attributes":[130],"such":[131],"as":[132],"sex":[133],"skin":[135,172],"tone,":[136],"transferred":[138],"domain":[141],"neutral":[144],"relative":[145],"attributes.":[148,163],"Furthermore,":[149],"predict":[154],"fairness":[155,177,193],"scores":[156],"with":[160],"unknown":[161],"sensitive":[162],"evaluate":[165],"our":[166,186],"framework":[167],"large-scale":[170],"public-available":[171],"lesion":[173],"dataset":[174],"under":[175],"various":[176],"evaluation":[178],"metrics.":[179],"The":[180],"experiments":[181],"demonstrate":[182],"effectiveness":[184],"proposed":[187],"method":[188],"estimating":[190],"improving":[192]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2021-03-15T00:00:00"}