Fair learning with Wasserstein barycenters for non-decomposable performance measures - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2023

Fair learning with Wasserstein barycenters for non-decomposable performance measures

Abstract

This work provides several fundamental characterizations of the optimal classification function under the demographic parity constraint. In the awareness framework, akin to the classical unconstrained classification case, we show that maximizing accuracy under this fairness constraint is equivalent to solving a corresponding regression problem followed by thresholding at level $1/2$. We extend this result to linear-fractional classification measures (e.g., ${\rm F}$-score, AM measure, balanced accuracy, etc.), highlighting the fundamental role played by the regression problem in this framework. Our results leverage recently developed connection between the demographic parity constraint and the multi-marginal optimal transport formulation. Informally, our result shows that the transition between the unconstrained problems and the fair one is achieved by replacing the conditional expectation of the label by the solution of the fair regression problem. Finally, leveraging our analysis, we demonstrate an equivalence between the awareness and the unawareness setups in the case of two sensitive groups.

Dates and versions

hal-03767640 , version 1 (02-09-2022)

Identifiers

Cite

Solenne Gaucher, Nicolas Schreuder, Evgenii Chzhen. Fair learning with Wasserstein barycenters for non-decomposable performance measures. AISTATS, Apr 2023, Valence (Espagne), Spain. pp.2436-2459. ⟨hal-03767640⟩
47 View
0 Download

Altmetric

Share

More