Fairness in Machine Learning

TL;DR

This paper explores advanced methods for ensuring fairness in machine learning, addressing limitations of current approaches by using causal Bayesian networks and optimal transport theory to develop more comprehensive and legally compliant fairness techniques.

Contribution

It introduces a unified framework incorporating causal Bayesian networks and optimal transport for improved fairness, with theoretical guarantees and methods for fair representation learning.

Findings

Causal Bayesian networks help reason about complex unfairness scenarios.

Optimal transport constrains distribution shapes for fairness.

Framework generalizes across different fairness criteria.

Abstract

Machine learning based systems are reaching society at large and in many aspects of everyday life. This phenomenon has been accompanied by concerns about the ethical issues that may arise from the adoption of these technologies. ML fairness is a recently established area of machine learning that studies how to ensure that biases in the data and model inaccuracies do not lead to models that treat individuals unfavorably on the basis of characteristics such as e.g. race, gender, disabilities, and sexual or political orientation. In this manuscript, we discuss some of the limitations present in the current reasoning about fairness and in methods that deal with it, and describe some work done by the authors to address them. More specifically, we show how causal Bayesian networks can play an important role to reason about and deal with fairness, especially in complex unfairness scenarios. We describe how optimal transport theory can be used to develop methods that impose constraints on the full shapes of distributions corresponding to different sensitive attributes, overcoming the limitation of most approaches that approximate fairness desiderata by imposing constraints on the lower order moments or other functions of those distributions. We present a unified framework that encompasses methods that can deal with different settings and fairness criteria, and that enjoys strong theoretical guarantees. We introduce an approach to learn fair representations that can generalize to unseen tasks. Finally, we describe a technique that accounts for legal restrictions about the use of sensitive attributes.