Matches in SemOpenAlex for { <https://semopenalex.org/work/W3214196913> ?p ?o ?g. }
- W3214196913 abstract "Increasing utilization of machine learning based decision support systems emphasizes the need for resulting predictions to be both accurate and fair to all stakeholders. In this work we present a novel approach to increase a Neural Network model's fairness during training. We introduce a family of fairness enhancing regularization components that we use in conjunction with the traditional binary-cross-entropy based accuracy loss. These loss functions are based on Bias Parity Score (BPS), a score that helps quantify bias in the models with a single number. In the current work we investigate the behavior and effect of these regularization components on bias. We deploy them in the context of a recidivism prediction task as well as on a census-based adult income dataset. The results demonstrate that with a good choice of fairness loss function we can reduce the trained model's bias without deteriorating accuracy even in unbalanced datasets." @default.
- W3214196913 created "2021-11-22" @default.
- W3214196913 creator A5031077789 @default.
- W3214196913 creator A5047174917 @default.
- W3214196913 creator A5067290650 @default.
- W3214196913 date "2023-05-08" @default.
- W3214196913 modified "2023-09-23" @default.
- W3214196913 title "Increasing Fairness in Predictions Using Bias Parity Score Based Loss Function Regularization" @default.
- W3214196913 cites W1453222892 @default.
- W3214196913 cites W1522301498 @default.
- W3214196913 cites W1559060276 @default.
- W3214196913 cites W1961345416 @default.
- W3214196913 cites W2014352947 @default.
- W3214196913 cites W2103780778 @default.
- W3214196913 cites W2116666691 @default.
- W3214196913 cites W2155982052 @default.
- W3214196913 cites W2162670686 @default.
- W3214196913 cites W2522104760 @default.
- W3214196913 cites W2530395818 @default.
- W3214196913 cites W2540757487 @default.
- W3214196913 cites W2725155646 @default.
- W3214196913 cites W2737032816 @default.
- W3214196913 cites W2752432442 @default.
- W3214196913 cites W2772070727 @default.
- W3214196913 cites W2785011159 @default.
- W3214196913 cites W2897978524 @default.
- W3214196913 cites W2909334458 @default.
- W3214196913 cites W2943613385 @default.
- W3214196913 cites W2945933015 @default.
- W3214196913 cites W2962750142 @default.
- W3214196913 cites W2963100392 @default.
- W3214196913 cites W2963116854 @default.
- W3214196913 cites W2963399222 @default.
- W3214196913 cites W2963718755 @default.
- W3214196913 cites W2979932536 @default.
- W3214196913 cites W3004493409 @default.
- W3214196913 cites W3046299928 @default.
- W3214196913 cites W3089931365 @default.
- W3214196913 cites W3095304749 @default.
- W3214196913 cites W3120740533 @default.
- W3214196913 cites W3123374861 @default.
- W3214196913 cites W3133726592 @default.
- W3214196913 cites W3134200737 @default.
- W3214196913 cites W3147041282 @default.
- W3214196913 cites W3181414820 @default.
- W3214196913 cites W2943071336 @default.
- W3214196913 doi "https://doi.org/10.32473/flairs.36.133311" @default.
- W3214196913 hasPublicationYear "2023" @default.
- W3214196913 type Work @default.
- W3214196913 sameAs 3214196913 @default.
- W3214196913 citedByCount "0" @default.
- W3214196913 crossrefType "journal-article" @default.
- W3214196913 hasAuthorship W3214196913A5031077789 @default.
- W3214196913 hasAuthorship W3214196913A5047174917 @default.
- W3214196913 hasAuthorship W3214196913A5067290650 @default.
- W3214196913 hasBestOaLocation W32141969131 @default.
- W3214196913 hasConcept C106301342 @default.
- W3214196913 hasConcept C119857082 @default.
- W3214196913 hasConcept C121332964 @default.
- W3214196913 hasConcept C12267149 @default.
- W3214196913 hasConcept C149782125 @default.
- W3214196913 hasConcept C154945302 @default.
- W3214196913 hasConcept C167981619 @default.
- W3214196913 hasConcept C2776135515 @default.
- W3214196913 hasConcept C33923547 @default.
- W3214196913 hasConcept C41008148 @default.
- W3214196913 hasConcept C48372109 @default.
- W3214196913 hasConcept C50644808 @default.
- W3214196913 hasConcept C62520636 @default.
- W3214196913 hasConcept C66905080 @default.
- W3214196913 hasConcept C94375191 @default.
- W3214196913 hasConcept C9679016 @default.
- W3214196913 hasConceptScore W3214196913C106301342 @default.
- W3214196913 hasConceptScore W3214196913C119857082 @default.
- W3214196913 hasConceptScore W3214196913C121332964 @default.
- W3214196913 hasConceptScore W3214196913C12267149 @default.
- W3214196913 hasConceptScore W3214196913C149782125 @default.
- W3214196913 hasConceptScore W3214196913C154945302 @default.
- W3214196913 hasConceptScore W3214196913C167981619 @default.
- W3214196913 hasConceptScore W3214196913C2776135515 @default.
- W3214196913 hasConceptScore W3214196913C33923547 @default.
- W3214196913 hasConceptScore W3214196913C41008148 @default.
- W3214196913 hasConceptScore W3214196913C48372109 @default.
- W3214196913 hasConceptScore W3214196913C50644808 @default.
- W3214196913 hasConceptScore W3214196913C62520636 @default.
- W3214196913 hasConceptScore W3214196913C66905080 @default.
- W3214196913 hasConceptScore W3214196913C94375191 @default.
- W3214196913 hasConceptScore W3214196913C9679016 @default.
- W3214196913 hasLocation W32141969131 @default.
- W3214196913 hasOpenAccess W3214196913 @default.
- W3214196913 hasPrimaryLocation W32141969131 @default.
- W3214196913 hasRelatedWork W1787221980 @default.
- W3214196913 hasRelatedWork W2379650135 @default.
- W3214196913 hasRelatedWork W2540388028 @default.
- W3214196913 hasRelatedWork W2972984751 @default.
- W3214196913 hasRelatedWork W3215867059 @default.
- W3214196913 hasRelatedWork W4224320362 @default.
- W3214196913 hasRelatedWork W4297899318 @default.
- W3214196913 hasRelatedWork W4302012992 @default.
- W3214196913 hasRelatedWork W4322008322 @default.