Fairness in Machine Learning
This paper tackles the problem of ensuring fair treatment by machine learning models for individuals, aiming to mitigate biases and inaccuracies that could lead to unfavorable outcomes based on sensitive characteristics.
This paper addresses the limitations in current machine learning fairness reasoning and methods. It proposes using causal Bayesian networks for complex unfairness scenarios, optimal transport theory to impose constraints on full distribution shapes, and a unified framework with strong theoretical guarantees. It also introduces an approach for learning fair representations that generalize to unseen tasks and a technique for accounting for legal restrictions on sensitive attributes.
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.