Wasserstein-based fairness interpretability framework for machine learning models
From MaRDI portal
Abstract: The objective of this article is to introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models at the level of a distribution. In our work, we measure the model bias across sub-population distributions in the model output using the Wasserstein metric. To properly quantify the contributions of predictors, we take into account the favorability of both the model and predictors with respect to the non-protected class. The quantification is accomplished by the use of transport theory, which gives rise to the decomposition of the model bias and bias explanations to positive and negative contributions. To gain more insight into the role of favorability and allow for additivity of bias explanations, we adapt techniques from cooperative game theory.
This page was built for publication: Wasserstein-based fairness interpretability framework for machine learning models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6353109)
