Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972124466> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2972124466 abstract "Fairness is becoming a rising concern w.r.t. machine learning model performance. Especially for sensitive fields such as criminal justice and loan decision, eliminating the prediction discrimination towards a certain group of population (characterized by sensitive features like race and gender) is important for enhancing the trustworthiness of model. In this paper, we present a new general framework to improve machine learning fairness. The goal of our model is to minimize the influence of sensitive feature from the perspectives of both the data input and the predictive model. In order to achieve this goal, we reformulate the data input by removing the sensitive information and strengthen model fairness by minimizing the marginal contribution of the sensitive feature. We propose to learn the non-sensitive input via sampling among features and design an adversarial network to minimize the dependence between the reformulated input and the sensitive information. Extensive experiments on three benchmark datasets suggest that our model achieve better results than related state-of-the-art methods with respect to both fairness metrics and prediction performance." @default.
- W2972124466 created "2019-09-12" @default.
- W2972124466 creator A5056184390 @default.
- W2972124466 creator A5060016795 @default.
- W2972124466 date "2019-09-06" @default.
- W2972124466 modified "2023-09-27" @default.
- W2972124466 title "Approaching Machine Learning Fairness through Adversarial Network." @default.
- W2972124466 cites W2014352947 @default.
- W2972124466 cites W2116984840 @default.
- W2972124466 cites W2159433000 @default.
- W2972124466 cites W2162670686 @default.
- W2972124466 cites W2166626454 @default.
- W2972124466 cites W2895471314 @default.
- W2972124466 cites W2904609718 @default.
- W2972124466 cites W2904642422 @default.
- W2972124466 cites W2962753953 @default.
- W2972124466 cites W2963116854 @default.
- W2972124466 cites W2963178340 @default.
- W2972124466 cites W2963454111 @default.
- W2972124466 cites W2964121744 @default.
- W2972124466 cites W3106076062 @default.
- W2972124466 cites W3120740533 @default.
- W2972124466 hasPublicationYear "2019" @default.
- W2972124466 type Work @default.
- W2972124466 sameAs 2972124466 @default.
- W2972124466 citedByCount "2" @default.
- W2972124466 countsByYear W29721244662020 @default.
- W2972124466 crossrefType "posted-content" @default.
- W2972124466 hasAuthorship W2972124466A5056184390 @default.
- W2972124466 hasAuthorship W2972124466A5060016795 @default.
- W2972124466 hasConcept C10138342 @default.
- W2972124466 hasConcept C119857082 @default.
- W2972124466 hasConcept C124101348 @default.
- W2972124466 hasConcept C13280743 @default.
- W2972124466 hasConcept C138885662 @default.
- W2972124466 hasConcept C144024400 @default.
- W2972124466 hasConcept C149923435 @default.
- W2972124466 hasConcept C154945302 @default.
- W2972124466 hasConcept C162324750 @default.
- W2972124466 hasConcept C185798385 @default.
- W2972124466 hasConcept C205649164 @default.
- W2972124466 hasConcept C2776401178 @default.
- W2972124466 hasConcept C2777764128 @default.
- W2972124466 hasConcept C2908647359 @default.
- W2972124466 hasConcept C37736160 @default.
- W2972124466 hasConcept C41008148 @default.
- W2972124466 hasConcept C41895202 @default.
- W2972124466 hasConceptScore W2972124466C10138342 @default.
- W2972124466 hasConceptScore W2972124466C119857082 @default.
- W2972124466 hasConceptScore W2972124466C124101348 @default.
- W2972124466 hasConceptScore W2972124466C13280743 @default.
- W2972124466 hasConceptScore W2972124466C138885662 @default.
- W2972124466 hasConceptScore W2972124466C144024400 @default.
- W2972124466 hasConceptScore W2972124466C149923435 @default.
- W2972124466 hasConceptScore W2972124466C154945302 @default.
- W2972124466 hasConceptScore W2972124466C162324750 @default.
- W2972124466 hasConceptScore W2972124466C185798385 @default.
- W2972124466 hasConceptScore W2972124466C205649164 @default.
- W2972124466 hasConceptScore W2972124466C2776401178 @default.
- W2972124466 hasConceptScore W2972124466C2777764128 @default.
- W2972124466 hasConceptScore W2972124466C2908647359 @default.
- W2972124466 hasConceptScore W2972124466C37736160 @default.
- W2972124466 hasConceptScore W2972124466C41008148 @default.
- W2972124466 hasConceptScore W2972124466C41895202 @default.
- W2972124466 hasLocation W29721244661 @default.
- W2972124466 hasOpenAccess W2972124466 @default.
- W2972124466 hasPrimaryLocation W29721244661 @default.
- W2972124466 hasRelatedWork W2785077884 @default.
- W2972124466 hasRelatedWork W2809701591 @default.
- W2972124466 hasRelatedWork W2894793033 @default.
- W2972124466 hasRelatedWork W2905029197 @default.
- W2972124466 hasRelatedWork W2924014439 @default.
- W2972124466 hasRelatedWork W2950104108 @default.
- W2972124466 hasRelatedWork W2962951800 @default.
- W2972124466 hasRelatedWork W2979999556 @default.
- W2972124466 hasRelatedWork W3007049821 @default.
- W2972124466 hasRelatedWork W3049579477 @default.
- W2972124466 hasRelatedWork W3128577869 @default.
- W2972124466 hasRelatedWork W3165183807 @default.
- W2972124466 hasRelatedWork W3167556547 @default.
- W2972124466 hasRelatedWork W3179976352 @default.
- W2972124466 hasRelatedWork W3187057914 @default.
- W2972124466 hasRelatedWork W3190688537 @default.
- W2972124466 hasRelatedWork W3194610661 @default.
- W2972124466 hasRelatedWork W3210973725 @default.
- W2972124466 hasRelatedWork W3212435167 @default.
- W2972124466 hasRelatedWork W2965119030 @default.
- W2972124466 isParatext "false" @default.
- W2972124466 isRetracted "false" @default.
- W2972124466 magId "2972124466" @default.
- W2972124466 workType "article" @default.