{"id":"https://openalex.org/W4401863501","doi":"https://doi.org/10.1145/3637528.3671991","title":"Using Self-supervised Learning Can Improve Model Fairness","display_name":"Using Self-supervised Learning Can Improve Model Fairness","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863501","doi":"https://doi.org/10.1145/3637528.3671991"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671991","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671991","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671991","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671991","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010623902","display_name":"Sofia Yfantidou","orcid":"https://orcid.org/0000-0002-5629-3493"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Sofia Yfantidou","raw_affiliation_strings":["Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030362528","display_name":"Dimitris Spathis","orcid":"https://orcid.org/0000-0001-9761-951X"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dimitris Spathis","raw_affiliation_strings":["Nokia Bell Labs, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012168451","display_name":"Marios Constantinides","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marios Constantinides","raw_affiliation_strings":["Nokia Bell Labs, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002623428","display_name":"Athena Vakali","orcid":"https://orcid.org/0000-0002-0666-6984"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athena Vakali","raw_affiliation_strings":["Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081008532","display_name":"Daniele Quercia","orcid":"https://orcid.org/0000-0001-9461-5804"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniele Quercia","raw_affiliation_strings":["Nokia Bell Labs, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210098141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053438231","display_name":"Fahim Kawsar","orcid":"https://orcid.org/0000-0001-5057-9557"},"institutions":[{"id":"https://openalex.org/I4210098141","display_name":"Nokia (United Kingdom)","ror":"https://ror.org/00zpf0626","country_code":"GB","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I4210098141"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fahim Kawsar","raw_affiliation_strings":["Nokia Bell Labs, Cambridge, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Nokia Bell Labs, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210098141"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010623902"],"corresponding_institution_ids":["https://openalex.org/I21370196"],"apc_list":null,"apc_paid":null,"fwci":1.5789,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86037136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3942","last_page":"3953"},"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":0.9907000064849854,"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":0.9907000064849854,"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":0.9629999995231628,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9589999914169312,"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/computer-science","display_name":"Computer science","score":0.7619028091430664},{"id":"https://openalex.org/keywords/fairness-measure","display_name":"Fairness measure","score":0.5539740324020386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4014661908149719},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37111103534698486},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.055348992347717285},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.05504313111305237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619028091430664},{"id":"https://openalex.org/C11867375","wikidata":"https://www.wikidata.org/wiki/Q5430671","display_name":"Fairness measure","level":4,"score":0.5539740324020386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4014661908149719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37111103534698486},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.055348992347717285},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.05504313111305237},{"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:10.1145/3637528.3671991","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671991","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671991","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671991","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671991","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671991","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863501.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1937674079","https://openalex.org/W2095695335","https://openalex.org/W2100960835","https://openalex.org/W2106413222","https://openalex.org/W2913939497","https://openalex.org/W2963026768","https://openalex.org/W2974817986","https://openalex.org/W3035164673","https://openalex.org/W3092143968","https://openalex.org/W3095351420","https://openalex.org/W3110080536","https://openalex.org/W3111737151","https://openalex.org/W3128981305","https://openalex.org/W3134970617","https://openalex.org/W3137991047","https://openalex.org/W3138416820","https://openalex.org/W3152436735","https://openalex.org/W3162391496","https://openalex.org/W4207057807","https://openalex.org/W4225323865","https://openalex.org/W4294891660","https://openalex.org/W4313156423","https://openalex.org/W4317542939","https://openalex.org/W4319837253","https://openalex.org/W4364381409","https://openalex.org/W4387821331","https://openalex.org/W4390871840","https://openalex.org/W4392971833"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,40],"(SSL)":[2],"has":[3],"become":[4],"the":[5,66,134,186,189],"de":[6],"facto":[7],"training":[8],"paradigm":[9],"of":[10,68,124],"large":[11],"models,":[12],"where":[13],"pre-training":[14,69],"is":[15],"followed":[16],"by":[17,120],"supervised":[18,30,157],"fine-tuning":[19,71,90],"using":[20],"domain-specific":[21,102],"data":[22],"and":[23,70,100,118,126,188],"labels.":[24],"Despite":[25],"demonstrating":[26],"comparable":[27],"performance":[28,153,170,202],"with":[29,91,156,166,200],"methods,":[31],"comprehensive":[32],"efforts":[33],"to":[34,137,160,181,194],"assess":[35],"SSL's":[36],"impact":[37,67],"on":[38,45,73,98,110,129,154],"machine":[39],"fairness":[41,78,165],"(i.e.,":[42,115],"performing":[43],"equally":[44],"different":[46],"demographic":[47],"breakdowns)":[48],"are":[49],"lacking.":[50],"Hypothesizing":[51],"that":[52,144,175],"SSL":[53,125,145],"models":[54,128],"would":[55],"learn":[56],"more":[57],"generic,":[58],"hence":[59],"less":[60],"biased":[61],"representations,":[62],"this":[63],"study":[64],"explores":[65],"strategies":[72],"fairness.":[74],"We":[75,105,173],"introduce":[76],"a":[77,161],"assessment":[79],"framework":[80],"for":[81,197],"SSL,":[82],"comprising":[83],"five":[84],"stages:":[85],"defining":[86],"dataset":[87],"requirements,":[88],"pre-training,":[89],"gradual":[92],"unfreezing,":[93],"assessing":[94],"representation":[95,182],"similarity":[96],"conditioned":[97],"demographics,":[99],"establishing":[101],"evaluation":[103,139],"processes.":[104],"evaluate":[106],"our":[107],"method's":[108],"generalizability":[109],"three":[111],"real-world":[112],"human-centric":[113],"datasets":[114],"MIMIC,":[116],"MESA,":[117],"GLOBEM)":[119],"systematically":[121],"comparing":[122],"hundreds":[123],"fine-tuned":[127],"various":[130],"dimensions":[131],"spanning":[132],"from":[133],"intermediate":[135],"representations":[136],"appropriate":[138],"metrics.":[140],"Our":[141],"findings":[142],"demonstrate":[143],"can":[146,178],"significantly":[147],"improve":[148],"model":[149],"fairness,":[150],"while":[151],"maintaining":[152],"par":[155],"methods-exhibiting":[158],"up":[159],"30%":[162],"increase":[163],"in":[164,169],"minimal":[167],"loss":[168],"through":[171],"self-supervision.":[172],"posit":[174],"such":[176],"differences":[177],"be":[179],"attributed":[180],"dissimilarities":[183],"found":[184],"between":[185,204],"best-":[187],"worst-performing":[190],"demographics":[191],"across":[192],"models-up":[193],"x13":[195],"greater":[196],"protected":[198],"attributes":[199],"larger":[201],"discrepancies":[203],"segments.":[205],"Code:":[206],"https://github.com/Nokia-Bell-Labs/SSLfairness":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}