Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221148703> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4221148703 abstract "Neural network architectures have been extensively employed in the fair representation learning setting, where the objective is to learn a new representation for a given vector which is independent of sensitive information. Various representation debiasing techniques have been proposed in the literature. However, as neural networks are inherently opaque, these methods are hard to comprehend, which limits their usefulness. We propose a new framework for fair representation learning which is centered around the learning of correction vectors, which have the same dimensionality as the given data vectors. The corrections are then simply summed up to the original features, and can therefore be analyzed as an explicit penalty or bonus to each feature. We show experimentally that a fair representation learning problem constrained in such a way does not impact performance." @default.
- W4221148703 created "2022-04-03" @default.
- W4221148703 creator A5023570168 @default.
- W4221148703 creator A5042265681 @default.
- W4221148703 creator A5071595380 @default.
- W4221148703 creator A5079960667 @default.
- W4221148703 date "2022-01-17" @default.
- W4221148703 modified "2023-09-27" @default.
- W4221148703 title "Fair Interpretable Learning via Correction Vectors" @default.
- W4221148703 doi "https://doi.org/10.48550/arxiv.2201.06343" @default.
- W4221148703 hasPublicationYear "2022" @default.
- W4221148703 type Work @default.
- W4221148703 citedByCount "0" @default.
- W4221148703 crossrefType "posted-content" @default.
- W4221148703 hasAuthorship W4221148703A5023570168 @default.
- W4221148703 hasAuthorship W4221148703A5042265681 @default.
- W4221148703 hasAuthorship W4221148703A5071595380 @default.
- W4221148703 hasAuthorship W4221148703A5079960667 @default.
- W4221148703 hasBestOaLocation W42211487031 @default.
- W4221148703 hasConcept C111030470 @default.
- W4221148703 hasConcept C119857082 @default.
- W4221148703 hasConcept C138885662 @default.
- W4221148703 hasConcept C154945302 @default.
- W4221148703 hasConcept C15744967 @default.
- W4221148703 hasConcept C17744445 @default.
- W4221148703 hasConcept C188147891 @default.
- W4221148703 hasConcept C199539241 @default.
- W4221148703 hasConcept C2776359362 @default.
- W4221148703 hasConcept C2776401178 @default.
- W4221148703 hasConcept C2779458634 @default.
- W4221148703 hasConcept C41008148 @default.
- W4221148703 hasConcept C41895202 @default.
- W4221148703 hasConcept C50644808 @default.
- W4221148703 hasConcept C59404180 @default.
- W4221148703 hasConcept C83665646 @default.
- W4221148703 hasConcept C94625758 @default.
- W4221148703 hasConceptScore W4221148703C111030470 @default.
- W4221148703 hasConceptScore W4221148703C119857082 @default.
- W4221148703 hasConceptScore W4221148703C138885662 @default.
- W4221148703 hasConceptScore W4221148703C154945302 @default.
- W4221148703 hasConceptScore W4221148703C15744967 @default.
- W4221148703 hasConceptScore W4221148703C17744445 @default.
- W4221148703 hasConceptScore W4221148703C188147891 @default.
- W4221148703 hasConceptScore W4221148703C199539241 @default.
- W4221148703 hasConceptScore W4221148703C2776359362 @default.
- W4221148703 hasConceptScore W4221148703C2776401178 @default.
- W4221148703 hasConceptScore W4221148703C2779458634 @default.
- W4221148703 hasConceptScore W4221148703C41008148 @default.
- W4221148703 hasConceptScore W4221148703C41895202 @default.
- W4221148703 hasConceptScore W4221148703C50644808 @default.
- W4221148703 hasConceptScore W4221148703C59404180 @default.
- W4221148703 hasConceptScore W4221148703C83665646 @default.
- W4221148703 hasConceptScore W4221148703C94625758 @default.
- W4221148703 hasLocation W42211487031 @default.
- W4221148703 hasOpenAccess W4221148703 @default.
- W4221148703 hasPrimaryLocation W42211487031 @default.
- W4221148703 hasRelatedWork W2078772520 @default.
- W4221148703 hasRelatedWork W2326464007 @default.
- W4221148703 hasRelatedWork W2556024076 @default.
- W4221148703 hasRelatedWork W2565262768 @default.
- W4221148703 hasRelatedWork W2898978534 @default.
- W4221148703 hasRelatedWork W2950554226 @default.
- W4221148703 hasRelatedWork W2963749793 @default.
- W4221148703 hasRelatedWork W4221148703 @default.
- W4221148703 hasRelatedWork W4224303442 @default.
- W4221148703 hasRelatedWork W4226165671 @default.
- W4221148703 isParatext "false" @default.
- W4221148703 isRetracted "false" @default.
- W4221148703 workType "article" @default.