{"id":"https://openalex.org/W2962925443","doi":"https://doi.org/10.1145/3306618.3314287","title":"Multiaccuracy","display_name":"Multiaccuracy","publication_year":2019,"publication_date":"2019-01-27","ids":{"openalex":"https://openalex.org/W2962925443","doi":"https://doi.org/10.1145/3306618.3314287","mag":"2962925443"},"language":"en","primary_location":{"id":"doi:10.1145/3306618.3314287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3306618.3314287","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3306618.3314287","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","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/10.1145/3306618.3314287","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039980118","display_name":"Michael P. Kim","orcid":"https://orcid.org/0000-0002-8269-854X"},"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":true,"raw_author_name":"Michael P. Kim","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034659013","display_name":"Amirata Ghorbani","orcid":"https://orcid.org/0000-0001-6465-2321"},"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":"Amirata Ghorbani","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"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":"James Zou","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039980118"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":14.45,"has_fulltext":true,"cited_by_count":182,"citation_normalized_percentile":{"value":0.99113929,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9983999729156494,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9983999729156494,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9907000064849854,"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":0.7226629257202148},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6956326961517334},{"id":"https://openalex.org/keywords/harm","display_name":"Harm","score":0.6462531089782715},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5550233125686646},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5499394536018372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5168417096138},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4935845136642456},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.47018635272979736},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46079760789871216},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3315296471118927},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.1233154833316803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226629257202148},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6956326961517334},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.6462531089782715},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5550233125686646},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5499394536018372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5168417096138},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4935845136642456},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.47018635272979736},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46079760789871216},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3315296471118927},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.1233154833316803},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3306618.3314287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3306618.3314287","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3306618.3314287","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3306618.3314287","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3306618.3314287","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3306618.3314287","source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G3252592884","display_name":null,"funder_award_id":"CCF-1763299","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3806200841","display_name":"AF: Medium: Collaborative Research:  Exploiting Opportunities in Pseudorandomness","funder_award_id":"1763299","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962925443.pdf","grobid_xml":"https://content.openalex.org/works/W2962925443.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1555759181","https://openalex.org/W1559060276","https://openalex.org/W1678356000","https://openalex.org/W1834627138","https://openalex.org/W1926592634","https://openalex.org/W1995897489","https://openalex.org/W2063083207","https://openalex.org/W2082704080","https://openalex.org/W2100960835","https://openalex.org/W2108263314","https://openalex.org/W2135481450","https://openalex.org/W2162670686","https://openalex.org/W2274287116","https://openalex.org/W2492794003","https://openalex.org/W2530395818","https://openalex.org/W2559655401","https://openalex.org/W2584805976","https://openalex.org/W2738456714","https://openalex.org/W2768894107","https://openalex.org/W2771004121","https://openalex.org/W2788481061","https://openalex.org/W2805956788","https://openalex.org/W2962739340","https://openalex.org/W2962922665","https://openalex.org/W2963178340","https://openalex.org/W2963323630","https://openalex.org/W2963475122","https://openalex.org/W2963818033","https://openalex.org/W2964031043","https://openalex.org/W2964247925","https://openalex.org/W2979452771","https://openalex.org/W3099206234","https://openalex.org/W4214821481","https://openalex.org/W4297944103","https://openalex.org/W4299828299","https://openalex.org/W6629411920","https://openalex.org/W6820668626"],"related_works":["https://openalex.org/W3203175338","https://openalex.org/W2356901839","https://openalex.org/W2404937507","https://openalex.org/W2030757640","https://openalex.org/W3121186197","https://openalex.org/W2373849942","https://openalex.org/W3209501579","https://openalex.org/W2047881532","https://openalex.org/W2285795935","https://openalex.org/W151161666"],"abstract_inverted_index":{"Prediction":[0],"systems":[1,26],"are":[2,188],"successfully":[3],"deployed":[4],"in":[5,43,81,162],"applications":[6,164],"ranging":[7],"from":[8],"disease":[9],"diagnosis,":[10],"to":[11,15,41,47,70,89,155,191],"predicting":[12],"credit":[13],"worthiness,":[14],"image":[16],"recognition.":[17],"Even":[18],"when":[19,115,181],"the":[20,44,54,116,131,141,150,153,157,182,192],"overall":[21],"accuracy":[22,158,175],"is":[23,118,134],"high,":[24],"these":[25],"may":[27,37],"exhibit":[28],"systematic":[29],"biases":[30,36],"that":[31,123,129],"harm":[32],"specific":[33],"subpopulations;":[34],"such":[35],"arise":[38],"inadvertently":[39],"due":[40],"underrepresentation":[42],"data":[45,99],"used":[46],"train":[48],"a":[49,62,90,93],"machine-learning":[50],"model,":[51],"or":[52],"as":[53],"result":[55],"of":[56,65,97,112,152],"intentional":[57],"malicious":[58],"discrimination.":[59],"We":[60,121,147],"develop":[61],"rigorous":[63],"framework":[64,105],"*multiaccuracy*":[66],"auditing":[67],"and":[68,92,110,127],"post-processing":[69],"ensure":[71],"accurate":[72,135],"predictions":[73],"across":[74],"*identifiable":[75],"subgroups*.":[76],"Our":[77],"algorithm,":[78],"MULTIACCURACY-BOOST,":[79],"works":[80],"any":[82],"setting":[83],"where":[84],"we":[85],"have":[86],"black-box":[87,104],"access":[88],"predictor":[91,117],"relatively":[94],"small":[95],"set":[96],"labeled":[98],"for":[100,107,177],"auditing;":[101],"importantly,":[102],"this":[103],"allows":[106],"improved":[108],"fairness":[109],"accountability":[111],"predictions,":[113],"even":[114,180],"minimally":[119],"transparent.":[120],"prove":[122],"MULTIACCURACY-BOOST":[124,171],"converges":[125],"efficiently":[126],"show":[128],"if":[130],"initial":[132],"model":[133,143],"on":[136],"an":[137],"identifiable":[138],"subgroup,":[139],"then":[140],"post-processed":[142],"will":[144],"be":[145],"also.":[146],"experimentally":[148],"demonstrate":[149],"effectiveness":[151],"approach":[154],"improve":[156,173],"among":[159],"minority":[160],"subgroups":[161],"diverse":[163],"(image":[165],"classification,":[166],"finance,":[167],"population":[168],"health).":[169],"Interestingly,":[170],"can":[172],"subpopulation":[174],"(e.g.":[176,185],"\"black":[178],"women\")":[179],"sensitive":[183],"features":[184],"\"race\",":[186],"\"gender\")":[187],"not":[189],"given":[190],"algorithm":[193],"explicitly.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":35},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2019-07-30T00:00:00"}