Fairness in Machine Learning: Lessons from Political Philosophy

TL;DR

This paper explores the concept of fairness in machine learning by drawing on moral and political philosophy to clarify different definitions and debates surrounding fairness, discrimination, and justice.

Contribution

It bridges philosophical theories with machine learning fairness definitions, providing a philosophical foundation for understanding and evaluating fairness criteria.

Findings

Highlights philosophical underpinnings of fairness concepts

Analyzes different fairness definitions and their assumptions

Connects moral philosophy with practical fairness debates

Abstract

What does it mean for a machine learning model to be `fair', in terms which can be operationalised? Should fairness consist of ensuring everyone has an equal probability of obtaining some benefit, or should we aim instead to minimise the harms to the least advantaged? Can the relevant ideal be determined by reference to some alternative state of affairs in which a particular social pattern of discrimination does not exist? Various definitions proposed in recent literature make different assumptions about what terms like discrimination and fairness mean and how they can be defined in mathematical terms. Questions of discrimination, egalitarianism and justice are of significant interest to moral and political philosophers, who have expended significant efforts in formalising and defending these central concepts. It is therefore unsurprising that attempts to formalise `fairness' in machine learning contain echoes of these old philosophical debates. This paper draws on existing work in moral and political philosophy in order to elucidate emerging debates about fair machine learning.