Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383312460> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4383312460 abstract "In this work, we present an end-to-end framework with a predictor model that provides classifier outputs from given input features and an adversary that tries to predict protected or sensitive features in order to mitigate intrinsic biases with respect to sensitive features (e.g., race, sex). Our proposed model increases the predictor’s capacity to produce correct predictions, while decreasing the adversary’s ability to anticipate sensitive features. We include a novel Semantic Attention (SA) module to the framework and demonstrate that our SA based Generative Adversarial Network (SAGAN) is able to significantly minimize the adversary’s capability to predict sensitive features, while retaining the predictor’s predictive accuracy. UCI Adult (Census) dataset was used a benchmark dataset for the testing. Our results demonstrate that the predictive model does not lose much accuracy, while achieving a Disparate Impact (DI) score very close to 1. The flexibility of the method makes it fitting to be applicable to a broad spectrum of gradient-based learning models, including both regression and classification tasks as well as different definitions of fairness. The source code for the implementation is available on github [1]." @default.
- W4383312460 created "2023-07-07" @default.
- W4383312460 creator A5033886992 @default.
- W4383312460 creator A5061570351 @default.
- W4383312460 creator A5064872950 @default.
- W4383312460 creator A5092409785 @default.
- W4383312460 date "2023-05-26" @default.
- W4383312460 modified "2023-10-08" @default.
- W4383312460 title "SAGAN: Maximizing Fairness using Semantic Attention Based Generative Adversarial Network" @default.
- W4383312460 cites W1961345416 @default.
- W4383312460 cites W2014352947 @default.
- W4383312460 cites W2032536435 @default.
- W4383312460 cites W2100960835 @default.
- W4383312460 cites W2116984840 @default.
- W4383312460 cites W2167655317 @default.
- W4383312460 cites W2550530154 @default.
- W4383312460 cites W2592677894 @default.
- W4383312460 cites W2963116854 @default.
- W4383312460 cites W2963290659 @default.
- W4383312460 cites W3096831136 @default.
- W4383312460 cites W4282572644 @default.
- W4383312460 doi "https://doi.org/10.1109/iciba56860.2023.10164925" @default.
- W4383312460 hasPublicationYear "2023" @default.
- W4383312460 type Work @default.
- W4383312460 citedByCount "0" @default.
- W4383312460 crossrefType "proceedings-article" @default.
- W4383312460 hasAuthorship W4383312460A5033886992 @default.
- W4383312460 hasAuthorship W4383312460A5061570351 @default.
- W4383312460 hasAuthorship W4383312460A5064872950 @default.
- W4383312460 hasAuthorship W4383312460A5092409785 @default.
- W4383312460 hasConcept C104317684 @default.
- W4383312460 hasConcept C105795698 @default.
- W4383312460 hasConcept C108583219 @default.
- W4383312460 hasConcept C119857082 @default.
- W4383312460 hasConcept C124101348 @default.
- W4383312460 hasConcept C13280743 @default.
- W4383312460 hasConcept C154945302 @default.
- W4383312460 hasConcept C185592680 @default.
- W4383312460 hasConcept C185798385 @default.
- W4383312460 hasConcept C205649164 @default.
- W4383312460 hasConcept C2780598303 @default.
- W4383312460 hasConcept C2988773926 @default.
- W4383312460 hasConcept C33923547 @default.
- W4383312460 hasConcept C37736160 @default.
- W4383312460 hasConcept C38652104 @default.
- W4383312460 hasConcept C39890363 @default.
- W4383312460 hasConcept C41008148 @default.
- W4383312460 hasConcept C41065033 @default.
- W4383312460 hasConcept C55493867 @default.
- W4383312460 hasConcept C63479239 @default.
- W4383312460 hasConcept C95623464 @default.
- W4383312460 hasConceptScore W4383312460C104317684 @default.
- W4383312460 hasConceptScore W4383312460C105795698 @default.
- W4383312460 hasConceptScore W4383312460C108583219 @default.
- W4383312460 hasConceptScore W4383312460C119857082 @default.
- W4383312460 hasConceptScore W4383312460C124101348 @default.
- W4383312460 hasConceptScore W4383312460C13280743 @default.
- W4383312460 hasConceptScore W4383312460C154945302 @default.
- W4383312460 hasConceptScore W4383312460C185592680 @default.
- W4383312460 hasConceptScore W4383312460C185798385 @default.
- W4383312460 hasConceptScore W4383312460C205649164 @default.
- W4383312460 hasConceptScore W4383312460C2780598303 @default.
- W4383312460 hasConceptScore W4383312460C2988773926 @default.
- W4383312460 hasConceptScore W4383312460C33923547 @default.
- W4383312460 hasConceptScore W4383312460C37736160 @default.
- W4383312460 hasConceptScore W4383312460C38652104 @default.
- W4383312460 hasConceptScore W4383312460C39890363 @default.
- W4383312460 hasConceptScore W4383312460C41008148 @default.
- W4383312460 hasConceptScore W4383312460C41065033 @default.
- W4383312460 hasConceptScore W4383312460C55493867 @default.
- W4383312460 hasConceptScore W4383312460C63479239 @default.
- W4383312460 hasConceptScore W4383312460C95623464 @default.
- W4383312460 hasLocation W43833124601 @default.
- W4383312460 hasOpenAccess W4383312460 @default.
- W4383312460 hasPrimaryLocation W43833124601 @default.
- W4383312460 hasRelatedWork W2913608505 @default.
- W4383312460 hasRelatedWork W2952541330 @default.
- W4383312460 hasRelatedWork W2952919291 @default.
- W4383312460 hasRelatedWork W2995778637 @default.
- W4383312460 hasRelatedWork W3024390022 @default.
- W4383312460 hasRelatedWork W3156291593 @default.
- W4383312460 hasRelatedWork W3198184493 @default.
- W4383312460 hasRelatedWork W3205696406 @default.
- W4383312460 hasRelatedWork W4287900812 @default.
- W4383312460 hasRelatedWork W4286901892 @default.
- W4383312460 isParatext "false" @default.
- W4383312460 isRetracted "false" @default.
- W4383312460 workType "article" @default.