FairnesswithoutHarm:DecoupledClassifierswithPreferenceGuaranteesBerkUstun1YangLiu2DavidC.Parkes1AbstractManyoftheproposedmethodsforfairmachinelearninghaveaimedtobuildmodelsthatpredictorperforminthe...
FairnessRiskMeasuresRobertC.Williamson1AdityaKrishnaMenon2AbstractabstractedearlierdefinitionsofFairnessbyframingtheprob-lemintermsofsubgrouplosses.Intuitively,theseworksEnsuringthatclassifiersaren...
CompositionalFairnessConstraintsforGraphEmbeddingsAvishekJoeyBose12WilliamL.Hamilton123AbstractSensitiveAttributesLearninghigh-qualitynodeembeddingsisakeybuildingblockformachinelearningmodelsthatGe...
PreventingFairnessGerrymandering:AuditingandLearningforSubgroupFairnessMichaelKearns1SethNeel1AaronRoth1ZhiweiStevenWu2AbstractOnemainattractionofstatisticaldefinitionsofFairnessisthattheycaninprin...
NonconvexOptimizationforRegressionwithFairnessConstraintsJunpeiKomiyama1AkikoTakeda12JunyaHonda12HajimeShimao3Abstractindefaultingonloans,directapplicationofmachinelearn-ingalgorithmwouldhighlylike...
FairnessWithoutDemographicsinRepeatedLossMinimizationTatsunoriB.Hashimoto12MeghaSrivastava1HongseokNamkoong3PercyLiang1AbstractJurgensetal.,2017),dependencyparsing(Blodgettetal.,2016),part-of-speec...
BlindJustice:FairnesswithEncryptedSensitiveAttributesNikiKilbertus12Adria`Gasco´n34MattKusner34MichaelVeale5KrishnaP.Gummadi6AdrianWeller23Abstractthishassomeintuitiveappealandjustification(Grgic...
MeritocraticFairnessforCross-PopulationSelectionMichaelKearns1AaronRoth1ZhiweiStevenWu1Abstractthenumberofcandidateseachyearissmall,simplycom-paringeachcandidatetotheirdirectcompetitorsthisyearWeco...
FairnessinReinforcementLearning⇤ShahinJabbariMatthewJosephMichaelKearnsJamieMorgensternAaronRoth1Abstracttingswherehistoricalcontextcanhaveadistinctinfluenceonthefuture.Forconcreteness,weconsidert...