Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890945214> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W2890945214 endingPage "3681" @default.
- W2890945214 startingPage "3671" @default.
- W2890945214 abstract "The Equalized Odds (for short, EO) is one of the most popular measures of discrimination used in the supervised learning setting. It ascertains fairness through the balance of the misclassification rates (false positive and negative) across the protected groups -- e.g., in the context of law enforcement, an African-American defendant who would not commit a future crime will have an equal opportunity of being released, compared to a non-recidivating Caucasian defendant. Despite this noble goal, it has been acknowledged in the literature that statistical tests based on the EO are oblivious to the underlying causal mechanisms that generated the disparity in the first place (Hardt et al. 2016). This leads to a critical disconnect between statistical measures readable from the data and the meaning of discrimination in the legal system, where compelling evidence that the observed disparity is tied to a specific causal process deemed unfair by society is required to characterize discrimination. The goal of this paper is to develop a principled approach to connect the statistical disparities characterized by the EO and the underlying, elusive, and frequently unobserved, causal mechanisms that generated such inequality. We start by introducing a new family of counterfactual measures that allows one to explain the misclassification disparities in terms of the underlying mechanisms in an arbitrary, non-parametric structural causal model. This will, in turn, allow legal and data analysts to interpret currently deployed classifiers through causal lens, linking the statistical disparities found in the data to the corresponding causal processes. Leveraging the new family of counterfactual measures, we develop a learning procedure to construct a classifier that is statistically efficient, interpretable, and compatible with the basic human intuition of fairness. We demonstrate our results through experiments in both real (COMPAS) and synthetic datasets." @default.
- W2890945214 created "2018-09-27" @default.
- W2890945214 creator A5039620960 @default.
- W2890945214 creator A5081473407 @default.
- W2890945214 date "2018-01-01" @default.
- W2890945214 modified "2023-10-18" @default.
- W2890945214 title "Equality of Opportunity in Classification: A Causal Approach" @default.
- W2890945214 hasPublicationYear "2018" @default.
- W2890945214 type Work @default.
- W2890945214 sameAs 2890945214 @default.
- W2890945214 citedByCount "16" @default.
- W2890945214 countsByYear W28909452142019 @default.
- W2890945214 countsByYear W28909452142020 @default.
- W2890945214 countsByYear W28909452142021 @default.
- W2890945214 countsByYear W28909452142022 @default.
- W2890945214 crossrefType "proceedings-article" @default.
- W2890945214 hasAuthorship W2890945214A5039620960 @default.
- W2890945214 hasAuthorship W2890945214A5081473407 @default.
- W2890945214 hasConcept C108650721 @default.
- W2890945214 hasConcept C119857082 @default.
- W2890945214 hasConcept C143095724 @default.
- W2890945214 hasConcept C149782125 @default.
- W2890945214 hasConcept C151956035 @default.
- W2890945214 hasConcept C153180980 @default.
- W2890945214 hasConcept C15744967 @default.
- W2890945214 hasConcept C162324750 @default.
- W2890945214 hasConcept C166957645 @default.
- W2890945214 hasConcept C205649164 @default.
- W2890945214 hasConcept C2779343474 @default.
- W2890945214 hasConcept C41008148 @default.
- W2890945214 hasConcept C71889745 @default.
- W2890945214 hasConcept C77088390 @default.
- W2890945214 hasConcept C77805123 @default.
- W2890945214 hasConceptScore W2890945214C108650721 @default.
- W2890945214 hasConceptScore W2890945214C119857082 @default.
- W2890945214 hasConceptScore W2890945214C143095724 @default.
- W2890945214 hasConceptScore W2890945214C149782125 @default.
- W2890945214 hasConceptScore W2890945214C151956035 @default.
- W2890945214 hasConceptScore W2890945214C153180980 @default.
- W2890945214 hasConceptScore W2890945214C15744967 @default.
- W2890945214 hasConceptScore W2890945214C162324750 @default.
- W2890945214 hasConceptScore W2890945214C166957645 @default.
- W2890945214 hasConceptScore W2890945214C205649164 @default.
- W2890945214 hasConceptScore W2890945214C2779343474 @default.
- W2890945214 hasConceptScore W2890945214C41008148 @default.
- W2890945214 hasConceptScore W2890945214C71889745 @default.
- W2890945214 hasConceptScore W2890945214C77088390 @default.
- W2890945214 hasConceptScore W2890945214C77805123 @default.
- W2890945214 hasLocation W28909452141 @default.
- W2890945214 hasOpenAccess W2890945214 @default.
- W2890945214 hasPrimaryLocation W28909452141 @default.
- W2890945214 hasRelatedWork W2100960835 @default.
- W2890945214 hasRelatedWork W2116666691 @default.
- W2890945214 hasRelatedWork W2143891888 @default.
- W2890945214 hasRelatedWork W2162670686 @default.
- W2890945214 hasRelatedWork W2530395818 @default.
- W2890945214 hasRelatedWork W2540757487 @default.
- W2890945214 hasRelatedWork W2750585749 @default.
- W2890945214 hasRelatedWork W2753845591 @default.
- W2890945214 hasRelatedWork W2788651580 @default.
- W2890945214 hasRelatedWork W2892038960 @default.
- W2890945214 hasRelatedWork W2912887944 @default.
- W2890945214 hasRelatedWork W2945670789 @default.
- W2890945214 hasRelatedWork W2962977061 @default.
- W2890945214 hasRelatedWork W2963453196 @default.
- W2890945214 hasRelatedWork W2963919086 @default.
- W2890945214 hasRelatedWork W2964031043 @default.
- W2890945214 hasRelatedWork W2964060106 @default.
- W2890945214 hasRelatedWork W2971251505 @default.
- W2890945214 hasRelatedWork W3001553940 @default.
- W2890945214 hasRelatedWork W3120740533 @default.
- W2890945214 hasVolume "31" @default.
- W2890945214 isParatext "false" @default.
- W2890945214 isRetracted "false" @default.
- W2890945214 magId "2890945214" @default.
- W2890945214 workType "article" @default.