Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034607623> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3034607623 abstract "The past few years have seen a dramatic rise of academic and societal interest in fair machine learning. While plenty of fair algorithms have been proposed recently to tackle this challenge for discrete variables, only a few ideas exist for continuous ones. The objective in this paper is to ensure some independence level between the outputs of regression models and any given continuous sensitive variables. For this purpose, we use the Hirschfeld-Gebelein-Rényi (HGR) maximal correlation coefficient as a fairness metric. We propose to minimize the HGR coefficient directly with an adversarial neural network architecture. The idea is to predict the output Y while minimizing the ability of an adversarial neural network to find the estimated transformations which are required to predict the HGR coefficient. We empirically assess and compare our approach and demonstrate significant improvements on previously presented work in the field." @default.
- W3034607623 created "2020-06-19" @default.
- W3034607623 creator A5008031795 @default.
- W3034607623 creator A5031635996 @default.
- W3034607623 creator A5065404842 @default.
- W3034607623 date "2020-07-01" @default.
- W3034607623 modified "2023-09-30" @default.
- W3034607623 title "Fairness-Aware Neural Rényi Minimization for Continuous Features" @default.
- W3034607623 cites W1972598934 @default.
- W3034607623 cites W2026019770 @default.
- W3034607623 cites W2040825624 @default.
- W3034607623 cites W2075277477 @default.
- W3034607623 cites W2092939357 @default.
- W3034607623 cites W2099471712 @default.
- W3034607623 cites W2145544165 @default.
- W3034607623 cites W2147981502 @default.
- W3034607623 cites W2162670686 @default.
- W3034607623 cites W2170862660 @default.
- W3034607623 cites W2483215953 @default.
- W3034607623 cites W2530395818 @default.
- W3034607623 cites W2546563948 @default.
- W3034607623 cites W2783047733 @default.
- W3034607623 cites W2810290439 @default.
- W3034607623 cites W2895471314 @default.
- W3034607623 cites W2946294136 @default.
- W3034607623 cites W2949194372 @default.
- W3034607623 cites W2955518298 @default.
- W3034607623 cites W2963100392 @default.
- W3034607623 cites W2963116854 @default.
- W3034607623 cites W2963174898 @default.
- W3034607623 cites W3098538463 @default.
- W3034607623 cites W3120740533 @default.
- W3034607623 cites W3122810052 @default.
- W3034607623 doi "https://doi.org/10.24963/ijcai.2020/313" @default.
- W3034607623 hasPublicationYear "2020" @default.
- W3034607623 type Work @default.
- W3034607623 sameAs 3034607623 @default.
- W3034607623 citedByCount "9" @default.
- W3034607623 countsByYear W30346076232021 @default.
- W3034607623 countsByYear W30346076232022 @default.
- W3034607623 crossrefType "proceedings-article" @default.
- W3034607623 hasAuthorship W3034607623A5008031795 @default.
- W3034607623 hasAuthorship W3034607623A5031635996 @default.
- W3034607623 hasAuthorship W3034607623A5065404842 @default.
- W3034607623 hasBestOaLocation W30346076231 @default.
- W3034607623 hasConcept C105795698 @default.
- W3034607623 hasConcept C119857082 @default.
- W3034607623 hasConcept C126255220 @default.
- W3034607623 hasConcept C147764199 @default.
- W3034607623 hasConcept C154945302 @default.
- W3034607623 hasConcept C162324750 @default.
- W3034607623 hasConcept C176217482 @default.
- W3034607623 hasConcept C199360897 @default.
- W3034607623 hasConcept C202444582 @default.
- W3034607623 hasConcept C21547014 @default.
- W3034607623 hasConcept C2780092901 @default.
- W3034607623 hasConcept C33923547 @default.
- W3034607623 hasConcept C35651441 @default.
- W3034607623 hasConcept C37736160 @default.
- W3034607623 hasConcept C41008148 @default.
- W3034607623 hasConcept C50644808 @default.
- W3034607623 hasConcept C83546350 @default.
- W3034607623 hasConcept C9652623 @default.
- W3034607623 hasConceptScore W3034607623C105795698 @default.
- W3034607623 hasConceptScore W3034607623C119857082 @default.
- W3034607623 hasConceptScore W3034607623C126255220 @default.
- W3034607623 hasConceptScore W3034607623C147764199 @default.
- W3034607623 hasConceptScore W3034607623C154945302 @default.
- W3034607623 hasConceptScore W3034607623C162324750 @default.
- W3034607623 hasConceptScore W3034607623C176217482 @default.
- W3034607623 hasConceptScore W3034607623C199360897 @default.
- W3034607623 hasConceptScore W3034607623C202444582 @default.
- W3034607623 hasConceptScore W3034607623C21547014 @default.
- W3034607623 hasConceptScore W3034607623C2780092901 @default.
- W3034607623 hasConceptScore W3034607623C33923547 @default.
- W3034607623 hasConceptScore W3034607623C35651441 @default.
- W3034607623 hasConceptScore W3034607623C37736160 @default.
- W3034607623 hasConceptScore W3034607623C41008148 @default.
- W3034607623 hasConceptScore W3034607623C50644808 @default.
- W3034607623 hasConceptScore W3034607623C83546350 @default.
- W3034607623 hasConceptScore W3034607623C9652623 @default.
- W3034607623 hasLocation W30346076231 @default.
- W3034607623 hasLocation W30346076232 @default.
- W3034607623 hasOpenAccess W3034607623 @default.
- W3034607623 hasPrimaryLocation W30346076231 @default.
- W3034607623 hasRelatedWork W2901368259 @default.
- W3034607623 hasRelatedWork W2903917280 @default.
- W3034607623 hasRelatedWork W2961085424 @default.
- W3034607623 hasRelatedWork W3046775127 @default.
- W3034607623 hasRelatedWork W4205705013 @default.
- W3034607623 hasRelatedWork W4285260836 @default.
- W3034607623 hasRelatedWork W4286629047 @default.
- W3034607623 hasRelatedWork W4306321456 @default.
- W3034607623 hasRelatedWork W4306674287 @default.
- W3034607623 hasRelatedWork W4224009465 @default.
- W3034607623 isParatext "false" @default.
- W3034607623 isRetracted "false" @default.
- W3034607623 magId "3034607623" @default.
- W3034607623 workType "article" @default.