{"id":"https://openalex.org/W4399362834","doi":"https://doi.org/10.1145/3630106.3659029","title":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","display_name":"Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4399362834","doi":"https://doi.org/10.1145/3630106.3659029"},"language":"en","primary_location":{"id":"doi:10.1145/3630106.3659029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3659029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3659029","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","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/10.1145/3630106.3659029","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094145958","display_name":"Sierra Wyllie","orcid":"https://orcid.org/0009-0000-1532-8840"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sierra Wyllie","raw_affiliation_strings":["University of Toronto and Vector Institute, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto and Vector Institute, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069844959","display_name":"Ilia Shumailov","orcid":"https://orcid.org/0000-0003-3100-0727"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ilia Shumailov","raw_affiliation_strings":["University of Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018809423","display_name":"Nicolas Papernot","orcid":"https://orcid.org/0000-0001-5078-7233"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nicolas Papernot","raw_affiliation_strings":["University of Toronto and Vector Institute, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto and Vector Institute, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5094145958"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":6.6724,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.96850307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2113","last_page":"2147"},"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":0.9983999729156494,"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":0.9983999729156494,"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":0.9959999918937683,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/redress","display_name":"Redress","score":0.7816338539123535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7318820357322693},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.4669220447540283},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.45270273089408875},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44826871156692505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4476161599159241},{"id":"https://openalex.org/keywords/performative-utterance","display_name":"Performative utterance","score":0.4274235665798187},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4102393388748169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3667905926704407}],"concepts":[{"id":"https://openalex.org/C2776515129","wikidata":"https://www.wikidata.org/wiki/Q7306218","display_name":"Redress","level":2,"score":0.7816338539123535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318820357322693},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.4669220447540283},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.45270273089408875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44826871156692505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4476161599159241},{"id":"https://openalex.org/C134141054","wikidata":"https://www.wikidata.org/wiki/Q965415","display_name":"Performative utterance","level":2,"score":0.4274235665798187},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4102393388748169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3667905926704407},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630106.3659029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3659029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3659029","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3630106.3659029","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3630106.3659029","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3630106.3659029","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2024 ACM Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3033334534","display_name":null,"funder_award_id":"AI Chair","funder_id":"https://openalex.org/F4320309949","funder_display_name":"Canadian Institute for Advanced Research"},{"id":"https://openalex.org/G5784215521","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399362834.pdf","grobid_xml":"https://content.openalex.org/works/W4399362834.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1975165783","https://openalex.org/W2007339694","https://openalex.org/W2090199150","https://openalex.org/W2116666691","https://openalex.org/W2529251251","https://openalex.org/W2530395818","https://openalex.org/W2584805976","https://openalex.org/W2998516762","https://openalex.org/W3004155201","https://openalex.org/W3012963798","https://openalex.org/W3120485916","https://openalex.org/W3133953502","https://openalex.org/W3135064756","https://openalex.org/W3165211483","https://openalex.org/W3213556453","https://openalex.org/W4224307605","https://openalex.org/W4226320345","https://openalex.org/W4230431391","https://openalex.org/W4250532311","https://openalex.org/W4288083800","https://openalex.org/W4297399259","https://openalex.org/W4312093654","https://openalex.org/W4312818733","https://openalex.org/W4366588458","https://openalex.org/W4380137202","https://openalex.org/W4386728952","https://openalex.org/W4390430574","https://openalex.org/W4390943985","https://openalex.org/W4392163191","https://openalex.org/W6728551298"],"related_works":["https://openalex.org/W4309241610","https://openalex.org/W4309241913","https://openalex.org/W2802821892","https://openalex.org/W2360901133","https://openalex.org/W2973293400","https://openalex.org/W1152665892","https://openalex.org/W3035069238","https://openalex.org/W3182611934","https://openalex.org/W2514264328","https://openalex.org/W4388067754"],"abstract_inverted_index":{"Model-induced":[0],"distribution":[1,45],"shifts":[2],"(MIDS)":[3],"occur":[4],"as":[5,21],"previous":[6],"model":[7,11,22,42],"outputs":[8],"pollute":[9],"new":[10],"training":[12,134],"sets":[13],"over":[14,74],"generations":[15],"of":[16,27,59,149],"models.":[17,39],"This":[18],"is":[19],"known":[20],"collapse":[23],"in":[24,84,92,111],"the":[25,56,147,171,177],"case":[26],"generative":[28],"models,":[29],"and":[30,53,87,151,167,185],"performative":[31],"prediction":[32],"or":[33],"unfairness":[34],"feedback":[35,173],"loops":[36,174],"for":[37,107,117,136,170],"supervised":[38],"When":[40],"a":[41,44,65,121],"induces":[43],"shift,":[46],"it":[47],"also":[48],"encodes":[49],"its":[50,60],"mistakes,":[51],"biases,":[52],"unfairnesses":[54,148],"into":[55],"ground":[57],"truth":[58],"data":[61,113,152],"ecosystem.":[62],"We":[63,127],"introduce":[64],"framework":[66,122],"that":[67,78,179],"allows":[68],"us":[69],"to":[70,82,140,155],"track":[71],"multiple":[72],"MIDS":[73],"many":[75],"generations,":[76],"finding":[77],"they":[79],"can":[80,144],"lead":[81],"loss":[83],"performance,":[85],"fairness,":[86],"minoritized":[88],"group":[89],"representation,":[90],"even":[91],"initially":[93],"unbiased":[94],"datasets.":[95],"Despite":[96],"these":[97],"negative":[98],"consequences,":[99],"we":[100],"identify":[101],"how":[102,142],"models":[103,150],"might":[104],"be":[105],"used":[106],"positive,":[108],"intentional,":[109],"interventions":[110,130],"their":[112],"ecosystems,":[114],"providing":[115],"redress":[116],"historical":[118],"discrimination":[119],"through":[120],"called":[123],"algorithmic":[124],"reparation":[125],"(AR).":[126],"simulate":[128],"AR":[129,143],"by":[131,176],"curating":[132],"representative":[133],"batches":[135],"stochastic":[137],"gradient":[138],"descent":[139],"demonstrate":[141],"improve":[145],"upon":[146],"ecosystems":[153],"subject":[154],"other":[156],"MIDS.":[157],"Our":[158],"work":[159],"takes":[160],"an":[161],"important":[162],"step":[163],"towards":[164],"identifying,":[165],"mitigating,":[166],"taking":[168],"accountability":[169],"unfair":[172],"enabled":[175],"idea":[178],"ML":[180],"systems":[181],"are":[182],"inherently":[183],"neutral":[184],"objective.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}