Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320166901> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4320166901 abstract "The popularity of machine learning has increased the risk of unfair models getting deployed in high-stake applications, such as justice system, drug/vaccination design, and medical diagnosis. Although there are effective methods to train fair models from scratch, how to automatically reveal and explain the unfairness of a trained model remains a challenging task. Revealing unfairness of machine learning models in interpretable fashion is a critical step towards fair and trustworthy AI. In this paper, we systematically tackle the novel task of revealing unfair models by mining interpretable evidence (RUMIE). The key idea is to find solid evidence in the form of a group of data instances discriminated most by the model. To make the evidence interpretable, we also find a set of human-understandable key attributes and decision rules that characterize the discriminated data instances and distinguish them from the other non-discriminated data. As demonstrated by extensive experiments on many real-world data sets, our method finds highly interpretable and solid evidence to effectively reveal the unfairness of trained models. Moreover, it is much more scalable than all of the baseline methods." @default.
- W4320166901 created "2023-02-13" @default.
- W4320166901 creator A5007946897 @default.
- W4320166901 creator A5015408396 @default.
- W4320166901 creator A5025153128 @default.
- W4320166901 creator A5028730873 @default.
- W4320166901 creator A5029599979 @default.
- W4320166901 creator A5057305433 @default.
- W4320166901 creator A5062247330 @default.
- W4320166901 creator A5064222660 @default.
- W4320166901 date "2022-07-12" @default.
- W4320166901 modified "2023-09-29" @default.
- W4320166901 title "Revealing Unfair Models by Mining Interpretable Evidence" @default.
- W4320166901 doi "https://doi.org/10.48550/arxiv.2207.05811" @default.
- W4320166901 hasPublicationYear "2022" @default.
- W4320166901 type Work @default.
- W4320166901 citedByCount "0" @default.
- W4320166901 crossrefType "posted-content" @default.
- W4320166901 hasAuthorship W4320166901A5007946897 @default.
- W4320166901 hasAuthorship W4320166901A5015408396 @default.
- W4320166901 hasAuthorship W4320166901A5025153128 @default.
- W4320166901 hasAuthorship W4320166901A5028730873 @default.
- W4320166901 hasAuthorship W4320166901A5029599979 @default.
- W4320166901 hasAuthorship W4320166901A5057305433 @default.
- W4320166901 hasAuthorship W4320166901A5062247330 @default.
- W4320166901 hasAuthorship W4320166901A5064222660 @default.
- W4320166901 hasBestOaLocation W43201669011 @default.
- W4320166901 hasConcept C111368507 @default.
- W4320166901 hasConcept C119857082 @default.
- W4320166901 hasConcept C124101348 @default.
- W4320166901 hasConcept C12725497 @default.
- W4320166901 hasConcept C127313418 @default.
- W4320166901 hasConcept C127413603 @default.
- W4320166901 hasConcept C153701036 @default.
- W4320166901 hasConcept C154945302 @default.
- W4320166901 hasConcept C15744967 @default.
- W4320166901 hasConcept C177264268 @default.
- W4320166901 hasConcept C199360897 @default.
- W4320166901 hasConcept C201995342 @default.
- W4320166901 hasConcept C2522767166 @default.
- W4320166901 hasConcept C26517878 @default.
- W4320166901 hasConcept C2780451532 @default.
- W4320166901 hasConcept C2780586970 @default.
- W4320166901 hasConcept C38652104 @default.
- W4320166901 hasConcept C41008148 @default.
- W4320166901 hasConcept C48044578 @default.
- W4320166901 hasConcept C77088390 @default.
- W4320166901 hasConcept C77805123 @default.
- W4320166901 hasConceptScore W4320166901C111368507 @default.
- W4320166901 hasConceptScore W4320166901C119857082 @default.
- W4320166901 hasConceptScore W4320166901C124101348 @default.
- W4320166901 hasConceptScore W4320166901C12725497 @default.
- W4320166901 hasConceptScore W4320166901C127313418 @default.
- W4320166901 hasConceptScore W4320166901C127413603 @default.
- W4320166901 hasConceptScore W4320166901C153701036 @default.
- W4320166901 hasConceptScore W4320166901C154945302 @default.
- W4320166901 hasConceptScore W4320166901C15744967 @default.
- W4320166901 hasConceptScore W4320166901C177264268 @default.
- W4320166901 hasConceptScore W4320166901C199360897 @default.
- W4320166901 hasConceptScore W4320166901C201995342 @default.
- W4320166901 hasConceptScore W4320166901C2522767166 @default.
- W4320166901 hasConceptScore W4320166901C26517878 @default.
- W4320166901 hasConceptScore W4320166901C2780451532 @default.
- W4320166901 hasConceptScore W4320166901C2780586970 @default.
- W4320166901 hasConceptScore W4320166901C38652104 @default.
- W4320166901 hasConceptScore W4320166901C41008148 @default.
- W4320166901 hasConceptScore W4320166901C48044578 @default.
- W4320166901 hasConceptScore W4320166901C77088390 @default.
- W4320166901 hasConceptScore W4320166901C77805123 @default.
- W4320166901 hasLocation W43201669011 @default.
- W4320166901 hasOpenAccess W4320166901 @default.
- W4320166901 hasPrimaryLocation W43201669011 @default.
- W4320166901 hasRelatedWork W1509467138 @default.
- W4320166901 hasRelatedWork W1527726406 @default.
- W4320166901 hasRelatedWork W1567031749 @default.
- W4320166901 hasRelatedWork W1995620535 @default.
- W4320166901 hasRelatedWork W2133515697 @default.
- W4320166901 hasRelatedWork W2327857945 @default.
- W4320166901 hasRelatedWork W2361492253 @default.
- W4320166901 hasRelatedWork W2975597301 @default.
- W4320166901 hasRelatedWork W3102755086 @default.
- W4320166901 hasRelatedWork W3134135808 @default.
- W4320166901 isParatext "false" @default.
- W4320166901 isRetracted "false" @default.
- W4320166901 workType "article" @default.