{"id":"https://openalex.org/W3205266373","doi":"https://doi.org/10.1109/bigdata55660.2022.10021107","title":"Fair Regression under Sample Selection Bias","display_name":"Fair Regression under Sample Selection Bias","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W3205266373","doi":"https://doi.org/10.1109/bigdata55660.2022.10021107","mag":"3205266373"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10021107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"2022 IEEE International Conference on Big Data (Big Data)","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/A5027505704","display_name":"Wei Du","orcid":"https://orcid.org/0000-0001-6284-6413"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Du","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA","University of Arkansas, Fayetteville, AR, USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008463509","display_name":"Xintao Wu","orcid":"https://orcid.org/0000-0002-2823-3063"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xintao Wu","raw_affiliation_strings":["University of Arkansas,Fayetteville,AR,USA","University of Arkansas, Fayetteville, AR, USA"],"affiliations":[{"raw_affiliation_string":"University of Arkansas,Fayetteville,AR,USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, Fayetteville, AR, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068043486","display_name":"Hanghang Tong","orcid":"https://orcid.org/0000-0003-4405-3887"},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanghang Tong","raw_affiliation_strings":["University of Illinois,Urbana,IL,USA","University of Illinois, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana,IL,USA","institution_ids":["https://openalex.org/I2801919071"]},{"raw_affiliation_string":"University of Illinois, Urbana, IL, USA","institution_ids":["https://openalex.org/I2801919071"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027505704"],"corresponding_institution_ids":["https://openalex.org/I78715868"],"apc_list":null,"apc_paid":null,"fwci":0.483,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67955801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1435","last_page":"1444"},"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":0.975600004196167,"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":0.975600004196167,"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/T10841","display_name":"Economic and Environmental Valuation","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9128999710083008,"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/mathematics","display_name":"Mathematics","score":0.5067954659461975},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5025589466094971},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.49811506271362305},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4610769748687744},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.45943209528923035},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4553958475589752},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.44016724824905396},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.4209926426410675},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40407681465148926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3839453458786011},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.34168481826782227},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.21307015419006348}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5067954659461975},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5025589466094971},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.49811506271362305},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4610769748687744},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.45943209528923035},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4553958475589752},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.44016724824905396},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.4209926426410675},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40407681465148926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3839453458786011},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.34168481826782227},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.21307015419006348},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10021107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10021107","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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":"2022 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W167258127","https://openalex.org/W1853837125","https://openalex.org/W1883968710","https://openalex.org/W2028138594","https://openalex.org/W2031811990","https://openalex.org/W2112483442","https://openalex.org/W2139122730","https://openalex.org/W2149754870","https://openalex.org/W2155982052","https://openalex.org/W2496083297","https://openalex.org/W2530395818","https://openalex.org/W2560674852","https://openalex.org/W2622808887","https://openalex.org/W2885501813","https://openalex.org/W2946294136","https://openalex.org/W2950145857","https://openalex.org/W2950664378","https://openalex.org/W2952399630","https://openalex.org/W2954569213","https://openalex.org/W2962922665","https://openalex.org/W2963327716","https://openalex.org/W2963940658","https://openalex.org/W2966384645","https://openalex.org/W2996829667","https://openalex.org/W2997398218","https://openalex.org/W2999905431","https://openalex.org/W3005657488","https://openalex.org/W3019370719","https://openalex.org/W3034607623","https://openalex.org/W3034955732","https://openalex.org/W3037521768","https://openalex.org/W3042376903","https://openalex.org/W3086700537","https://openalex.org/W3102808026","https://openalex.org/W3103373783","https://openalex.org/W3125601827","https://openalex.org/W3198906045","https://openalex.org/W3209838760","https://openalex.org/W4250589301","https://openalex.org/W4288300526","https://openalex.org/W4386564359","https://openalex.org/W6676264761","https://openalex.org/W6682197734","https://openalex.org/W6723554050","https://openalex.org/W6728551298","https://openalex.org/W6738996040","https://openalex.org/W6748377460","https://openalex.org/W6748716324","https://openalex.org/W6751691900","https://openalex.org/W6753999205","https://openalex.org/W6757904846","https://openalex.org/W6762559389","https://openalex.org/W6763398819","https://openalex.org/W6763593068","https://openalex.org/W6765858885","https://openalex.org/W6773884429","https://openalex.org/W6775903094","https://openalex.org/W6779823592","https://openalex.org/W6780319689"],"related_works":["https://openalex.org/W4293088233","https://openalex.org/W2496077116","https://openalex.org/W3152660226","https://openalex.org/W3082212156","https://openalex.org/W4243140484","https://openalex.org/W4388813866","https://openalex.org/W1986523067","https://openalex.org/W2900695351","https://openalex.org/W2307799538","https://openalex.org/W3115592149"],"abstract_inverted_index":{"Recent":[0],"research":[1,33],"on":[2,6,123,217],"fair":[3,31,75],"regression":[4,26,32,76,121],"focused":[5],"developing":[7],"new":[8],"fairness":[9,119,127,154,164,186,235],"notions":[10,165],"and":[11,17,38,64,113,136,156,166,190,202,221,234],"approximation":[12],"methods":[13],"as":[14,96],"target":[15],"variables":[16],"even":[18],"the":[19,25,35,44,57,62,91,106,114,132,142,168,174,178,183,222,226],"sensitive":[20],"attribute":[21],"are":[22,41,94],"continuous":[23],"in":[24,52,120,229],"setting.":[27],"However,":[28],"all":[29],"previous":[30],"assumed":[34],"training":[36,63,92],"data":[37,40,93],"testing":[39,65],"drawn":[42],"from":[43,90],"same":[45],"distributions.":[46],"This":[47],"assumption":[48],"is":[49],"often":[50],"violated":[51],"real":[53],"world":[54],"due":[55],"to":[56,117,147,159,172],"sample":[58,78,133,149],"selection":[59,79,134,150],"bias":[60,80,111],"between":[61],"data.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,195,206],"develop":[71],"a":[72,86,97,124,138,161],"framework":[73,104],"for":[74,110,203],"under":[77],"when":[81],"dependent":[82],"variable":[83,140],"values":[84],"of":[85,88,99,126,163,210,231],"set":[87],"samples":[89],"missing":[95],"result":[98],"another":[100],"hidden":[101],"process.":[102],"Our":[103],"adopts":[105],"classic":[107],"Heckman":[108,129],"model":[109,130],"correction":[112],"Lagrange":[115,169],"duality":[116,170],"achieve":[118],"based":[122],"variety":[125,162],"notions.":[128],"describes":[131],"process":[135],"uses":[137],"derived":[139],"called":[141],"Inverse":[143],"Mills":[144],"Ratio":[145],"(IMR)":[146],"correct":[148],"bias.":[151],"We":[152,214],"use":[153],"inequality":[155],"equality":[157],"constraints":[158],"describe":[160],"apply":[167],"theory":[171],"transform":[173],"primal":[175],"problem":[176],"into":[177],"dual":[179],"convex":[180],"optimization.":[181],"For":[182],"two":[184],"popular":[185],"notions,":[187],"mean":[188,191],"difference":[189],"squared":[192],"error":[193],"difference,":[194],"derive":[196,207],"explicit":[197],"formulas":[198],"without":[199],"iterative":[200],"optimization,":[201],"Pearson":[204],"correlation,":[205],"its":[208],"conditions":[209],"achieving":[211],"strong":[212],"duality.":[213],"conduct":[215],"experiments":[216],"three":[218],"real-world":[219],"datasets":[220],"experimental":[223],"results":[224],"demonstrate":[225],"approach\u2019s":[227],"effectiveness":[228],"terms":[230],"both":[232],"utility":[233],"metrics.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}