Fairness in Machine Learning: Lessons from Political Philosophy

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.

References in corpus (1)

• Equality of Opportunity in Supervised Learning

Cited by in corpus (21)

• Improving fairness in machine learning systems: What do industry practitioners need?
• A Survey of End-to-End Driving: Architectures and Training Methods
• Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models
• Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Escaping the Impossibility of Fairness: From Formal to Substantive Algorithmic Fairness
• Fairness and Decision-making in Collaborative Shift Scheduling Systems
• Fairness in machine learning: against false positive rate equality as a measure of fairness
• FairGAN: Fairness-aware Generative Adversarial Networks
• Adversarial Attacks on Machine Learning Systems for High-Frequency Trading
• The Bouncer Problem: Challenges to Remote Explainability
• Reflexive Design for Fairness and Other Human Values in Formal Models
• Questioning the assumptions behind fairness solutions
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• Personalized explanation in machine learning: A conceptualization
• Data and Model Dependencies of Membership Inference Attack
• Future Illiteracies -- Architectural Epistemology and Artificial Intelligence
• Technical Challenges for Training Fair Neural Networks
• Analyzing Fairness of Computer Vision and Natural Language Processing Models
• Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance
• Equalizing Financial Impact in Supervised Learning