{"id":"https://openalex.org/W6910004780","doi":"https://doi.org/10.3929/ethz-b-000557060","title":"Fairness-Aware PAC Learning from Corrupted Data","display_name":"Fairness-Aware PAC Learning from Corrupted Data","publication_year":2021,"publication_date":"2021-02-11","ids":{"openalex":"https://openalex.org/W6910004780","doi":"https://doi.org/10.3929/ethz-b-000557060","mag":"3126339915"},"language":"en","primary_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/557060","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/557060","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Machine Learning Research, 23","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11850/557060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088091013","display_name":"Nikola Konstantinov","orcid":"https://orcid.org/0009-0009-5204-7621","observed_orcids":["https://orcid.org/0009-0009-5204-7621"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konstantinov, Nikola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Lampert, Christoph H.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lampert, Christoph H.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5841,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6816579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7914999723434448,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.7914999723434448,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.08609999716281891,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.01209999993443489,"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/algorithmic-fairness","display_name":"algorithmic fairness","score":0.9290000200271606},{"id":"https://openalex.org/keywords/pac-learning","display_name":"PAC learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/data-corruption","display_name":"data corruption","score":0.8339999914169312},{"id":"https://openalex.org/keywords/hardness-of-learning","display_name":"hardness of learning","score":0.5770000219345093},{"id":"https://openalex.org/keywords/fairness-accuracy-trade-off","display_name":"fairness-accuracy trade-off","score":0.7229999899864197}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6894999742507935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6477000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5717999935150146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5419999957084656},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/557060","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/557060","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Machine Learning Research, 23","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2102.06004","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06004","pdf_url":"https://arxiv.org/pdf/2102.06004","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"mag:3126339915","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.06004.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.06004","doi":"https://doi.org/10.48550/arxiv.2102.06004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06004","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.3929/ethz-b-000557060","doi":"https://doi.org/10.3929/ethz-b-000557060","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000557060","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/557060","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/557060","pdf_url":null,"source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Machine Learning Research, 23","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7578999996185303,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6910004780.pdf","grobid_xml":"https://content.openalex.org/works/W6910004780.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1766442844","https://openalex.org/W1968998685","https://openalex.org/W1977696979","https://openalex.org/W2097246321","https://openalex.org/W2103012681","https://openalex.org/W2107189314","https://openalex.org/W2111296615","https://openalex.org/W2112507308","https://openalex.org/W2116666691","https://openalex.org/W2118025696","https://openalex.org/W2156909104","https://openalex.org/W2180443860","https://openalex.org/W2530395818","https://openalex.org/W2554864439","https://openalex.org/W2594166818","https://openalex.org/W2626801932","https://openalex.org/W2773446523","https://openalex.org/W2774423163","https://openalex.org/W2785495800","https://openalex.org/W2790025105","https://openalex.org/W2803923024","https://openalex.org/W2804815760","https://openalex.org/W2809969113","https://openalex.org/W2909334458","https://openalex.org/W2911736639","https://openalex.org/W2914344555","https://openalex.org/W2918374197","https://openalex.org/W2962863665","https://openalex.org/W2962922665","https://openalex.org/W2963327716","https://openalex.org/W2964135521","https://openalex.org/W2969896603","https://openalex.org/W3003137157","https://openalex.org/W3007366319","https://openalex.org/W3014986830","https://openalex.org/W3017348803","https://openalex.org/W3031684522","https://openalex.org/W3034986954","https://openalex.org/W3035729345","https://openalex.org/W3037134569","https://openalex.org/W3042376903","https://openalex.org/W3083540916","https://openalex.org/W3095542981","https://openalex.org/W3099070140","https://openalex.org/W3099803834","https://openalex.org/W3101867941","https://openalex.org/W3111128105","https://openalex.org/W3132032427","https://openalex.org/W3167938804","https://openalex.org/W3172963091","https://openalex.org/W4223454493","https://openalex.org/W4236362309"],"related_works":["https://openalex.org/W3126339915","https://openalex.org/W7132347784","https://openalex.org/W6943734735","https://openalex.org/W4385261061","https://openalex.org/W4287115227","https://openalex.org/W3035729345","https://openalex.org/W2911457688","https://openalex.org/W3177106777","https://openalex.org/W4223454493","https://openalex.org/W2951476734"],"abstract_inverted_index":{"Addressing":[0],"fairness":[1,130],"concerns":[2],"about":[3,34],"machine":[4],"learning":[5,49,93,122],"models":[6,28],"is":[7,32],"a":[8],"crucial":[9],"step":[10],"towards":[11],"their":[12],"long-term":[13],"adoption":[14],"in":[15,60,99,141,152],"real-world":[16],"automated":[17],"systems.":[18],"While":[19],"many":[20],"approaches":[21],"have":[22],"been":[23],"developed":[24],"for":[25,92,126],"training":[26],"fair":[27],"from":[29],"data,":[30],"little":[31],"known":[33],"the":[35,74,85,88,100,144,148,153],"robustness":[36],"of":[37,73,87,143],"these":[38,134],"methods":[39],"to":[40,66,112],"data":[41,52,155],"corruption.":[42],"In":[43],"this":[44,116],"work":[45],"we":[46,118],"consider":[47],"fairness-aware":[48],"under":[50],"worst-case":[51],"manipulations.":[53],"We":[54,102],"show":[55,132],"that":[56,84,105,124,133,138],"an":[57,68],"adversary":[58],"can":[59],"some":[61],"situations":[62],"force":[63],"any":[64],"learner":[65],"return":[67],"overly":[69],"biased":[70],"classifier,":[71],"regardless":[72],"sample":[75],"size":[76],"and":[77,83,129,131,147],"with":[78,95],"or":[79],"without":[80],"degrading":[81],"accuracy,":[82],"strength":[86],"excess":[89],"bias":[90],"increases":[91],"problems":[94],"underrepresented":[96],"protected":[97,149],"groups":[98,150],"data.":[101],"also":[103],"prove":[104],"our":[106],"hardness":[107],"results":[108],"are":[109,139],"tight":[110],"up":[111],"constant":[113],"factors.":[114],"To":[115],"end,":[117],"study":[119],"two":[120],"natural":[121],"algorithms":[123,135],"optimize":[125],"both":[127],"accuracy":[128],"enjoy":[136],"guarantees":[137],"order-optimal":[140],"terms":[142],"corruption":[145],"ratio":[146],"frequencies":[151],"large":[154],"limit.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}