English

Loss Balancing for Fair Supervised Learning

Machine Learning 2023-11-08 v1 Artificial Intelligence

Abstract

Supervised learning models have been used in various domains such as lending, college admission, face recognition, natural language processing, etc. However, they may inherit pre-existing biases from training data and exhibit discrimination against protected social groups. Various fairness notions have been proposed to address unfairness issues. In this work, we focus on Equalized Loss (EL), a fairness notion that requires the expected loss to be (approximately) equalized across different groups. Imposing EL on the learning process leads to a non-convex optimization problem even if the loss function is convex, and the existing fair learning algorithms cannot properly be adopted to find the fair predictor under the EL constraint. This paper introduces an algorithm that can leverage off-the-shelf convex programming tools (e.g., CVXPY) to efficiently find the global optimum of this non-convex optimization. In particular, we propose the ELminimizer algorithm, which finds the optimal fair predictor under EL by reducing the non-convex optimization to a sequence of convex optimization problems. We theoretically prove that our algorithm finds the global optimal solution under certain conditions. Then, we support our theoretical results through several empirical studies.

Keywords

Cite

@article{arxiv.2311.03714,
  title  = {Loss Balancing for Fair Supervised Learning},
  author = {Mohammad Mahdi Khalili and Xueru Zhang and Mahed Abroshan},
  journal= {arXiv preprint arXiv:2311.03714},
  year   = {2023}
}

Comments

This paper has been published in the Fortieth International Conference on Machine Learning (ICML 2023)

R2 v1 2026-06-28T13:13:35.786Z