Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132514446> ?p ?o ?g. }
- W3132514446 abstract "As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To respond to these concerns, the community has proposed and formalized various notions of fairness as well as methods for rectifying unfair behavior. While fairness constraints have been studied extensively for classical models, the effectiveness of methods for imposing fairness on deep neural networks is unclear. In this paper, we observe that these large models overfit to fairness objectives, and produce a range of unintended and undesirable consequences. We conduct our experiments on both facial recognition and automated medical diagnosis datasets using state-of-the-art architectures." @default.
- W3132514446 created "2021-03-01" @default.
- W3132514446 creator A5048896019 @default.
- W3132514446 creator A5060687985 @default.
- W3132514446 creator A5066564672 @default.
- W3132514446 creator A5071538560 @default.
- W3132514446 creator A5083834808 @default.
- W3132514446 date "2021-02-12" @default.
- W3132514446 modified "2023-09-25" @default.
- W3132514446 title "Technical Challenges for Training Fair Neural Networks." @default.
- W3132514446 cites W2014352947 @default.
- W3132514446 cites W2100960835 @default.
- W3132514446 cites W2116666691 @default.
- W3132514446 cites W2117539524 @default.
- W3132514446 cites W2126400421 @default.
- W3132514446 cites W2530395818 @default.
- W3132514446 cites W2540757487 @default.
- W3132514446 cites W2609296554 @default.
- W3132514446 cites W2725155646 @default.
- W3132514446 cites W2730550703 @default.
- W3132514446 cites W2768894107 @default.
- W3132514446 cites W2773523653 @default.
- W3132514446 cites W2788284633 @default.
- W3132514446 cites W2788416960 @default.
- W3132514446 cites W2788481061 @default.
- W3132514446 cites W2789467142 @default.
- W3132514446 cites W2794342582 @default.
- W3132514446 cites W2810873347 @default.
- W3132514446 cites W2889295596 @default.
- W3132514446 cites W2904183610 @default.
- W3132514446 cites W2920646515 @default.
- W3132514446 cites W2937229771 @default.
- W3132514446 cites W2962688627 @default.
- W3132514446 cites W2962898354 @default.
- W3132514446 cites W2963053914 @default.
- W3132514446 cites W2963327716 @default.
- W3132514446 cites W2963351448 @default.
- W3132514446 cites W2963446712 @default.
- W3132514446 cites W2963803533 @default.
- W3132514446 cites W2963818033 @default.
- W3132514446 cites W2964023221 @default.
- W3132514446 cites W2964031043 @default.
- W3132514446 cites W2969985801 @default.
- W3132514446 cites W2985936223 @default.
- W3132514446 cites W2990751682 @default.
- W3132514446 cites W3004542466 @default.
- W3132514446 cites W3004604609 @default.
- W3132514446 cites W3007679811 @default.
- W3132514446 cites W3034214983 @default.
- W3132514446 cites W3034256900 @default.
- W3132514446 cites W3034700241 @default.
- W3132514446 cites W3034879135 @default.
- W3132514446 cites W3034927672 @default.
- W3132514446 cites W3035026192 @default.
- W3132514446 cites W3035729345 @default.
- W3132514446 cites W3035765133 @default.
- W3132514446 cites W3037294637 @default.
- W3132514446 cites W3048511172 @default.
- W3132514446 cites W3099361686 @default.
- W3132514446 cites W3099803834 @default.
- W3132514446 cites W3100618246 @default.
- W3132514446 cites W3123847197 @default.
- W3132514446 cites W3126068903 @default.
- W3132514446 cites W3134893036 @default.
- W3132514446 cites W3137695714 @default.
- W3132514446 hasPublicationYear "2021" @default.
- W3132514446 type Work @default.
- W3132514446 sameAs 3132514446 @default.
- W3132514446 citedByCount "1" @default.
- W3132514446 countsByYear W31325144462021 @default.
- W3132514446 crossrefType "posted-content" @default.
- W3132514446 hasAuthorship W3132514446A5048896019 @default.
- W3132514446 hasAuthorship W3132514446A5060687985 @default.
- W3132514446 hasAuthorship W3132514446A5066564672 @default.
- W3132514446 hasAuthorship W3132514446A5071538560 @default.
- W3132514446 hasAuthorship W3132514446A5083834808 @default.
- W3132514446 hasConcept C108583219 @default.
- W3132514446 hasConcept C119857082 @default.
- W3132514446 hasConcept C127413603 @default.
- W3132514446 hasConcept C146978453 @default.
- W3132514446 hasConcept C154945302 @default.
- W3132514446 hasConcept C17744445 @default.
- W3132514446 hasConcept C199539241 @default.
- W3132514446 hasConcept C204323151 @default.
- W3132514446 hasConcept C22019652 @default.
- W3132514446 hasConcept C2776889888 @default.
- W3132514446 hasConcept C2984842247 @default.
- W3132514446 hasConcept C41008148 @default.
- W3132514446 hasConcept C50644808 @default.
- W3132514446 hasConceptScore W3132514446C108583219 @default.
- W3132514446 hasConceptScore W3132514446C119857082 @default.
- W3132514446 hasConceptScore W3132514446C127413603 @default.
- W3132514446 hasConceptScore W3132514446C146978453 @default.
- W3132514446 hasConceptScore W3132514446C154945302 @default.
- W3132514446 hasConceptScore W3132514446C17744445 @default.
- W3132514446 hasConceptScore W3132514446C199539241 @default.
- W3132514446 hasConceptScore W3132514446C204323151 @default.
- W3132514446 hasConceptScore W3132514446C22019652 @default.
- W3132514446 hasConceptScore W3132514446C2776889888 @default.
- W3132514446 hasConceptScore W3132514446C2984842247 @default.