{"id":"https://openalex.org/W4412825784","doi":"https://doi.org/10.1145/3711896.3736846","title":"Are Your Fairness Metrics Accurate? A Semi-Supervised Approach to Improving Fairness Estimates Under Sample Selection Bias","display_name":"Are Your Fairness Metrics Accurate? A Semi-Supervised Approach to Improving Fairness Estimates Under Sample Selection Bias","publication_year":2025,"publication_date":"2025-08-01","ids":{"openalex":"https://openalex.org/W4412825784","doi":"https://doi.org/10.1145/3711896.3736846"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3711896.3736846","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085991432","display_name":"M. Clara De Paolis Kaluza","orcid":"https://orcid.org/0000-0003-2376-6669"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Clara De Paolis Kaluza","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0003-2376-6669","affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039286471","display_name":"Thulasi Tholeti","orcid":"https://orcid.org/0000-0001-7213-9050"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thulasi Tholeti","raw_affiliation_strings":["Institute for Experiential AI, Northeastern University, Boston, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0001-7213-9050","affiliations":[{"raw_affiliation_string":"Institute for Experiential AI, Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060645310","display_name":"Y. Allen Chen","orcid":"https://orcid.org/0000-0003-4406-1166"},"institutions":[{"id":"https://openalex.org/I2801852214","display_name":"University of Washington Medical Center","ror":"https://ror.org/00wbzw723","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2801852214"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yile Chen","raw_affiliation_strings":["Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington, USA"],"raw_orcid":"https://orcid.org/0000-0003-4406-1166","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, Washington, USA","institution_ids":["https://openalex.org/I2801852214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076204770","display_name":"Ricardo Baeza\u2010Yates","orcid":"https://orcid.org/0000-0003-3208-9778"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ricardo Baeza-Yates","raw_affiliation_strings":["AI Institute, Barcelona Supercomputing Center, Barcelona, Catalonia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-3208-9778","affiliations":[{"raw_affiliation_string":"AI Institute, Barcelona Supercomputing Center, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051324698","display_name":"Predrag Radivojac","orcid":"https://orcid.org/0000-0002-6769-0793"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Predrag Radivojac","raw_affiliation_strings":["Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0002-6769-0793","affiliations":[{"raw_affiliation_string":"Khoury College of Computer Sciences, Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100664534","display_name":"Shantanu Jain","orcid":"https://orcid.org/0000-0002-7169-9483"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shantanu Jain","raw_affiliation_strings":["Institute for Experiential AI, Northeastern University, Boston, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0002-7169-9483","affiliations":[{"raw_affiliation_string":"Institute for Experiential AI, Northeastern University, Boston, Massachusetts, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"450"},"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":0.9927999973297119,"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":0.9927999973297119,"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/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13051","display_name":"Qualitative Comparative Analysis Research","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697661817073822},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6960341930389404},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.6251235008239746},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6034755110740662},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.4551016390323639},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3692013621330261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3344552516937256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33402830362319946},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16509485244750977},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.08466961979866028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697661817073822},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6960341930389404},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.6251235008239746},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6034755110740662},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.4551016390323639},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3692013621330261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3344552516937256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33402830362319946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16509485244750977},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.08466961979866028},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3736846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736846","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736846","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2282436710","display_name":null,"funder_award_id":"U01HG012022","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W189742998","https://openalex.org/W1527373413","https://openalex.org/W2011111286","https://openalex.org/W2049633694","https://openalex.org/W2051978340","https://openalex.org/W2059748199","https://openalex.org/W2100960835","https://openalex.org/W2117853077","https://openalex.org/W2141253686","https://openalex.org/W2174602966","https://openalex.org/W2405607598","https://openalex.org/W2516720184","https://openalex.org/W2590957573","https://openalex.org/W2760062370","https://openalex.org/W2809878087","https://openalex.org/W2924489771","https://openalex.org/W2932671560","https://openalex.org/W2963160524","https://openalex.org/W2963275094","https://openalex.org/W2990138404","https://openalex.org/W3027202947","https://openalex.org/W3029661147","https://openalex.org/W3094376731","https://openalex.org/W3104285666","https://openalex.org/W3169530247","https://openalex.org/W3181414820","https://openalex.org/W3209838760","https://openalex.org/W4205164650","https://openalex.org/W4210736086","https://openalex.org/W4225161546","https://openalex.org/W4247082009","https://openalex.org/W4283168161","https://openalex.org/W4287825762","https://openalex.org/W4296548734","https://openalex.org/W4309643822","https://openalex.org/W4316038168","https://openalex.org/W4382202913","https://openalex.org/W4392044215","https://openalex.org/W4396790789","https://openalex.org/W4402220283","https://openalex.org/W4405648826","https://openalex.org/W4408707833","https://openalex.org/W6775444529","https://openalex.org/W7044050609"],"related_works":["https://openalex.org/W2361713743","https://openalex.org/W2136050782","https://openalex.org/W2114851664","https://openalex.org/W2147625294","https://openalex.org/W2138888940","https://openalex.org/W4205762803","https://openalex.org/W2374431462","https://openalex.org/W2535856026","https://openalex.org/W1884218869","https://openalex.org/W2159994411"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"impeding":[3],"the":[4,12,18,35,78,130,157,215,239],"widespread":[5],"deployment":[6,64],"of":[7,14,34,47,55,65,86,217,241],"machine":[8],"learning":[9],"is":[10,49,69,81],"overcoming":[11],"impact":[13],"statistical":[15],"biases":[16],"in":[17,84,156,220],"data.":[19,133,226],"Models":[20],"trained":[21],"on":[22,43,113,202,224],"unrepresentative":[23],"data":[24,80],"can":[25,99],"perform":[26],"worse":[27],"than":[28],"anticipated":[29],"and":[30,39,169,192,211,237],"differentially":[31],"affect":[32],"cross-sections":[33],"population.":[36],"Therefore,":[37],"evaluating":[38],"vetting":[40],"models":[41,164],"based":[42],"an":[44,116,185],"appropriate":[45],"notion":[46],"fairness":[48,56,74,95,206,240],"often":[50,70],"indispensable,":[51],"making":[52],"accurate":[53],"estimation":[54,126],"metrics":[57],"a":[58,73,121,137,148,173],"critical":[59],"step":[60],"to":[61,91,115,124,151,162,188,234],"safeguard":[62],"against":[63],"unfair":[66],"algorithms.":[67],"It":[68],"assumed":[71],"that":[72,146],"metric":[75,96],"computed":[76],"from":[77,129],"observed":[79],"accurate.":[82],"However,":[83],"presence":[85],"selection":[87,139],"bias,":[88],"also":[89],"referred":[90],"as":[92,166],"distributional":[93,154],"shifts,":[94],"estimates":[97,223],"too":[98],"have":[100],"systematic":[101],"application-specific":[102],"errors.":[103],"In":[104],"this":[105,109],"work":[106],"we":[107,135,182,228],"demonstrate":[108,214],"phenomenon":[110],"and,":[111],"relying":[112],"access":[114],"unbiased":[117,198],"unlabeled":[118],"data,":[119,159],"derive":[120,184],"semi-supervised":[122],"approach":[123,219,233],"mitigate":[125],"errors":[127],"emerging":[128],"biased":[131],"labeled":[132],"Specifically,":[134],"introduce":[136],"novel":[138],"bias":[140,231],"model":[141,190],"called":[142],"''sub-class-conditional":[143],"invariance''":[144],"(SCC-invariance),":[145],"offers":[147],"flexible":[149],"framework":[150],"effectively":[152],"capture":[153],"shifts":[155],"real-world":[158],"particularly":[160],"compared":[161],"traditional":[163],"such":[165],"label":[167],"shift":[168],"covariate":[170],"shift.":[171],"Assuming":[172],"finite":[174],"Gaussian":[175],"mixture":[176],"form":[177],"for":[178,196],"each":[179],"class-conditional":[180],"distribution,":[181],"then":[183],"Expectation-Maximization":[186],"algorithm":[187],"estimate":[189],"parameters":[191],"correction":[193],"weights":[194],"necessary":[195],"computing":[197],"estimates.":[199],"We":[200],"focus":[201],"three":[203],"widely":[204],"used":[205],"metrics--equal":[207],"opportunity,":[208],"predictive":[209,212],"equality,":[210],"parity--and":[213],"effectiveness":[216],"our":[218,230],"improving":[221],"their":[222],"synthetic":[225],"Finally,":[227],"apply":[229],"mitigation":[232],"clinical":[235],"genetics":[236],"study":[238],"pathogenicity":[242],"predictors":[243],"across":[244],"ancestral":[245],"groups.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}