{"id":"https://openalex.org/W4288083803","doi":"https://doi.org/10.1145/3351095.3375709","title":"Towards fairer datasets","display_name":"Towards fairer datasets","publication_year":2020,"publication_date":"2020-01-27","ids":{"openalex":"https://openalex.org/W4288083803","doi":"https://doi.org/10.1145/3351095.3375709"},"language":"en","primary_location":{"id":"doi:10.1145/3351095.3375709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3351095.3375709","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3351095.3375709&file=p547-yang-supp.pdf&download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3351095.3375709&file=p547-yang-supp.pdf&download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103883065","display_name":"Kaiyu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiyu Yang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043062005","display_name":"Klint Qinami","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Klint Qinami","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450462","display_name":"Li Fei-Fei","orcid":"https://orcid.org/0000-0002-7481-0810"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fei-Fei","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542158","display_name":"Jia Deng","orcid":"https://orcid.org/0000-0001-9594-4554"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Deng","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022811687","display_name":"Olga Russakovsky","orcid":"https://orcid.org/0000-0001-5272-3241"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Russakovsky","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.9607,"has_fulltext":true,"cited_by_count":226,"citation_normalized_percentile":{"value":0.99454002,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"547","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9818000197410583,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9818000197410583,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9751999974250793,"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":0.9714999794960022,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.621862530708313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.621862530708313}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3351095.3375709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3351095.3375709","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3351095.3375709&file=p547-yang-supp.pdf&download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.07726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.07726","pdf_url":"https://arxiv.org/pdf/1912.07726","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:10.1145/3351095.3375709","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3351095.3375709","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F3351095.3375709&file=p547-yang-supp.pdf&download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1451479478","display_name":null,"funder_award_id":"1763642","funder_id":"https://openalex.org/F4320309090","funder_display_name":"Center for Hierarchical Manufacturing, National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320309090","display_name":"Center for Hierarchical Manufacturing, National Science Foundation","ror":"https://ror.org/043trmd87"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288083803.pdf","grobid_xml":"https://content.openalex.org/works/W4288083803.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1819662813","https://openalex.org/W1834627138","https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1949778830","https://openalex.org/W1965804146","https://openalex.org/W1970737474","https://openalex.org/W2014352947","https://openalex.org/W2026019770","https://openalex.org/W2031342017","https://openalex.org/W2031489346","https://openalex.org/W2040825624","https://openalex.org/W2048859817","https://openalex.org/W2049626874","https://openalex.org/W2052301699","https://openalex.org/W2055999471","https://openalex.org/W2064600544","https://openalex.org/W2073679637","https://openalex.org/W2086240363","https://openalex.org/W2097246321","https://openalex.org/W2100960835","https://openalex.org/W2108598243","https://openalex.org/W2116666691","https://openalex.org/W2117539524","https://openalex.org/W2125416623","https://openalex.org/W2145607950","https://openalex.org/W2147561019","https://openalex.org/W2149252982","https://openalex.org/W2156493807","https://openalex.org/W2157928966","https://openalex.org/W2167683722","https://openalex.org/W2194775991","https://openalex.org/W2274815471","https://openalex.org/W2275130673","https://openalex.org/W2277195237","https://openalex.org/W2602855788","https://openalex.org/W2732026016","https://openalex.org/W2783946743","https://openalex.org/W2895472239","https://openalex.org/W2907374781","https://openalex.org/W2962787423","https://openalex.org/W2962933664","https://openalex.org/W2963037989","https://openalex.org/W2963116854","https://openalex.org/W2963349562","https://openalex.org/W4231815665","https://openalex.org/W4234425342","https://openalex.org/W4254494015","https://openalex.org/W4288617757","https://openalex.org/W6638208828"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Computer":[0],"vision":[1,21,35,83,105],"technology":[2],"is":[3],"being":[4],"used":[5],"by":[6],"many":[7,80],"but":[8],"remains":[9],"representative":[10],"of":[11,19,43,72,79,94,112,120,129,143],"only":[12],"a":[13,69],"few.":[14],"People":[15],"have":[16],"reported":[17],"misbehavior":[18],"computer":[20,34,82,104],"models,":[22],"including":[23],"offensive":[24],"prediction":[25],"results":[26],"and":[27,51,125,146],"lower":[28],"performance":[29],"for":[30],"underrepresented":[31],"groups.":[32],"Current":[33],"models":[36],"are":[37,57],"typically":[38],"developed":[39],"using":[40],"datasets":[41,56],"consisting":[42],"manually":[44],"annotated":[45],"images":[46,73,133],"or":[47],"videos;":[48],"the":[49,60,77,91,108,115,127,132,140,148],"data":[50],"label":[52],"distributions":[53],"in":[54,102,131],"these":[55,144],"critical":[58],"to":[59,99,138,151],"models'":[61],"behavior.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"examine":[67],"ImageNet,":[68],"large-scale":[70],"ontology":[71],"that":[74,96],"has":[75],"spurred":[76],"development":[78],"modern":[81],"methods.":[84],"We":[85,136],"consider":[86],"three":[87],"key":[88],"factors":[89],"within":[90,134],"person":[92],"subtree":[93],"ImageNet":[95],"may":[97],"lead":[98],"problematic":[100],"behavior":[101],"downstream":[103],"technology:":[106],"(1)":[107],"stagnant":[109],"concept":[110],"vocabulary":[111],"WordNet,":[113],"(2)":[114],"attempt":[116],"at":[117],"exhaustive":[118],"illustration":[119],"all":[121],"categories":[122],"with":[123],"images,":[124],"(3)":[126],"inequality":[128],"representation":[130],"concepts.":[135],"seek":[137],"illuminate":[139],"root":[141],"causes":[142],"concerns":[145],"take":[147],"first":[149],"steps":[150],"mitigate":[152],"them":[153],"constructively.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":43},{"year":2022,"cited_by_count":52},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":9}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2022-07-28T00:00:00"}