English

fairret: a Framework for Differentiable Fairness Regularization Terms

Machine Learning 2024-04-11 v2

Abstract

Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.

Keywords

Cite

@article{arxiv.2310.17256,
  title  = {fairret: a Framework for Differentiable Fairness Regularization Terms},
  author = {Maarten Buyl and MaryBeth Defrance and Tijl De Bie},
  journal= {arXiv preprint arXiv:2310.17256},
  year   = {2024}
}

Comments

Presented at ICLR 2024

R2 v1 2026-06-28T13:02:33.351Z