{"id":"https://openalex.org/W4225776270","doi":"https://doi.org/10.1145/3616855.3635844","title":"FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes","display_name":"FairIF: Boosting Fairness in Deep Learning via Influence Functions with Validation Set Sensitive Attributes","publication_year":2024,"publication_date":"2024-03-04","ids":{"openalex":"https://openalex.org/W4225776270","doi":"https://doi.org/10.1145/3616855.3635844"},"language":"en","primary_location":{"id":"doi:10.1145/3616855.3635844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635844","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635844","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635844","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100342615","display_name":"Haonan Wang","orcid":"https://orcid.org/0009-0006-6963-8987"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Haonan Wang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101794936","display_name":"Ziwei Wu","orcid":"https://orcid.org/0000-0003-3999-4367"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziwei Wu","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073158087","display_name":"Jingrui He","orcid":"https://orcid.org/0000-0002-6429-6272"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingrui He","raw_affiliation_strings":["School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100342615"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.7034,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8533791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"721","last_page":"730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9908999800682068,"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/boosting","display_name":"Boosting (machine learning)","score":0.9062609672546387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7236257791519165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405904054641724},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.5292871594429016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47471439838409424},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4566532373428345},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.06329849362373352},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.050561219453811646}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.9062609672546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236257791519165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405904054641724},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.5292871594429016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47471439838409424},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4566532373428345},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.06329849362373352},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.050561219453811646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1145/3616855.3635844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635844","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635844","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2201.05759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.05759","pdf_url":"https://arxiv.org/pdf/2201.05759","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1145/3616855.3635844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3616855.3635844","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3616855.3635844","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1366408413","display_name":null,"funder_award_id":"211790","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1528967963","display_name":"III: Small: Predictive Analysis of Diabetes Dedicated Social Networks","funder_award_id":"2002540","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1835150374","display_name":null,"funder_award_id":"IIS-1947203, IIS-2117902, IIS-2137468, and IIS-2002540","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G360821608","display_name":"EAGER: Weakly Supervised Graph Neural Networks","funder_award_id":"2137468","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7286171126","display_name":null,"funder_award_id":"1947203","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7374246537","display_name":"III: Small: RareXplain: A Computational Framework for Explainable Rare Category Analysis","funder_award_id":"2117902","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225776270.pdf","grobid_xml":"https://content.openalex.org/works/W4225776270.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W607505555","https://openalex.org/W1538170657","https://openalex.org/W1834627138","https://openalex.org/W2014352947","https://openalex.org/W2100960835","https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2271982975","https://openalex.org/W2507358938","https://openalex.org/W2530395818","https://openalex.org/W2547875792","https://openalex.org/W2566079294","https://openalex.org/W2597603852","https://openalex.org/W2744999500","https://openalex.org/W2786599105","https://openalex.org/W2787955716","https://openalex.org/W2788241675","https://openalex.org/W2797558164","https://openalex.org/W2897080984","https://openalex.org/W2899771611","https://openalex.org/W2904642422","https://openalex.org/W2909334458","https://openalex.org/W2910603373","https://openalex.org/W2911752833","https://openalex.org/W2947285452","https://openalex.org/W2949200088","https://openalex.org/W2962790618","https://openalex.org/W2963116854","https://openalex.org/W2982232682","https://openalex.org/W2995793065","https://openalex.org/W3032949543","https://openalex.org/W3034700241","https://openalex.org/W3037881973","https://openalex.org/W3092541244","https://openalex.org/W3094239814","https://openalex.org/W3118560954","https://openalex.org/W3120485916","https://openalex.org/W3120740533","https://openalex.org/W3131061281","https://openalex.org/W3132556242","https://openalex.org/W3165292502","https://openalex.org/W3167556547","https://openalex.org/W3181414820","https://openalex.org/W3184352888","https://openalex.org/W3186518531","https://openalex.org/W3193448347","https://openalex.org/W4220760463","https://openalex.org/W4281258849","https://openalex.org/W4281988409","https://openalex.org/W4283165383","https://openalex.org/W4283205676","https://openalex.org/W4283779208","https://openalex.org/W4287123704","https://openalex.org/W4287728672","https://openalex.org/W4287753323","https://openalex.org/W4288091850","https://openalex.org/W4289258088","https://openalex.org/W4289438483","https://openalex.org/W4297795193","https://openalex.org/W4298102393","https://openalex.org/W4311639009","https://openalex.org/W4385681731"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Empirical":[0,166],"loss":[1,125],"minimization":[2],"during":[3,137,221],"machine":[4,28],"learning":[5,29],"training":[6,37,49,57,76,91],"can":[7],"inadvertently":[8],"introduce":[9],"bias,":[10],"stemming":[11],"from":[12,69],"discrimination":[13],"and":[14,162,171,182,214],"societal":[15],"prejudices":[16],"present":[17,44],"in":[18,120],"the":[19,23,61,75,104,116,124,130,203,222],"data.":[20,92,106],"To":[21],"address":[22],"shortcomings":[24],"of":[25,36,133,196,205],"traditional":[26],"fair":[27],"methods-which":[30],"often":[31],"rely":[32],"on":[33,103,144,168],"sensitive":[34,67,90],"information":[35,68],"data":[38],"or":[39,88,123,199],"mandate":[40],"significant":[41],"model":[42,121,177],"alterations-we":[43],"FairIF,":[45],"a":[46,70,112,141],"unique":[47],"two-stage":[48],"framework.":[50],"Distinctly,":[51],"FairIF":[52,94,134,206],"enhances":[53],"fairness":[54,96,131],"by":[55,100,110],"recalibrating":[56],"sample":[58],"weights":[59],"using":[60],"influence":[62],"function.":[63,126],"Notably,":[64],"it":[65],"employs":[66],"validation":[71],"set,":[72,77],"rather":[73],"than":[74],"to":[78,192,207,217],"determine":[79],"these":[80],"weights.":[81],"This":[82],"approach":[83],"accommodates":[84],"situations":[85],"with":[86,139],"missing":[87],"inaccessible":[89],"Our":[93],"ensures":[95],"across":[97,175],"demographic":[98],"groups":[99],"retraining":[101],"models":[102,210],"reweighted":[105],"It":[107],"stands":[108],"out":[109],"offering":[111],"plug-and-play":[113],"solution,":[114],"obviating":[115],"need":[117],"for":[118,211],"changes":[119],"architecture":[122],"We":[127],"demonstrate":[128],"that":[129,150],"performance":[132],"is":[135],"guaranteed":[136],"testing":[138],"only":[140],"minimal":[142],"impact":[143],"classification":[145],"performance.":[146],"Additionally,":[147],"we":[148],"analyze":[149],"our":[151,229],"framework":[152],"adeptly":[153],"addresses":[154],"issues":[155],"like":[156],"group":[157],"size":[158,164],"disparities,":[159],"distribution":[160],"shifts,":[161],"class":[163],"discrepancies.":[165],"evaluations":[167],"three":[169],"synthetic":[170],"five":[172],"real-world":[173],"datasets":[174],"six":[176],"architectures":[178],"confirm":[179],"FairIF's":[180],"efficiency":[181],"scalability.":[183],"The":[184],"experimental":[185],"results":[186],"indicate":[187],"superior":[188],"fairness-utility":[189],"trade-offs":[190],"compared":[191],"other":[193],"methods,":[194],"regardless":[195],"bias":[197],"types":[198],"architectural":[200],"variations.":[201],"Moreover,":[202],"adaptability":[204],"utilize":[208],"pretrained":[209],"subsequent":[212],"tasks":[213],"its":[215],"capability":[216],"rectify":[218],"unfairness":[219],"originating":[220],"pretraining":[223],"phase":[224],"are":[225],"further":[226],"validated":[227],"through":[228],"experiments.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2022-05-05T00:00:00"}