Shapley meets Rawls: an integrated framework for measuring and explaining unfairness

Read full text Summarise with VIRAT
Authors: Fadoua Amri-Jouidel, Emmanuel Kemel, Stéphane Mussard
Cited by: 0
References: 45

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Explainability and fairness have mainly been considered separately, with recent exceptions trying the explain the sources of unfairness. This paper shows that the Shapley value can be used to both define and explain unfairness, under standard group fairness criteria. This offers an integrated framework to estimate and derive inference on unfairness as-well-as the features that contribute to it. Our framework can also be extended from Shapley values to the family of Efficient-Symmetric-Linear (ESL) values, some of which offer more robust definitions of fairness, and shorter computation times. An illustration is run on the Census Income dataset from the UCI Machine Learning Repository. Our approach shows that ``Age", ``Number of hours" and ``Marital status" generate gender unfairness, using shorter computation time than traditional Bootstrap tests.

Fields of Study & Subjects

Ethics and Social Impacts of AI Explainable Artificial Intelligence (XAI) Game Theory and Voting Systems

Publication details

Journal / source
arXiv (Cornell University)
Publication date
27 March 2026
Language
EN
Document type
Preprint