From Parity to Preference-based Notions of Fairness in Classification

Abstract

The adoption of automated, data-driven decision making in an ever expanding range of applications has raised concerns about its potential unfairness towards certain social groups. In this context, a number of recent studies have focused on defining, detecting, and removing unfairness from data-driven decision systems. However, the existing notions of fairness, based on parity (equality) in treatment or outcomes for different social groups, tend to be quite stringent, limiting the overall decision making accuracy. In this paper, we draw inspiration from the fair-division and envy-freeness literature in economics and game theory and propose preference-based notions of fairness -- given the choice between various sets of decision treatments or outcomes, any group of users would collectively prefer its treatment or outcomes, regardless of the (dis)parity as compared to the other groups. Then, we introduce tractable proxies to design margin-based classifiers that satisfy these preference-based notions of fairness. Finally, we experiment with a variety of synthetic and real-world datasets and show that preference-based fairness allows for greater decision accuracy than parity-based fairness.

To appear in Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017). Code available at: https://github.com/mbilalzafar/fair-classification

Cited by in corpus (17)

• Fairness in Machine Learning
• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
• Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learning
• Fairness risk measures
• Review of Mathematical frameworks for Fairness in Machine Learning
• Ethical Adversaries: Towards Mitigating Unfairness with Adversarial Machine Learning
• Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing
• Unintended Selection: Persistent Qualification Rate Disparities and Interventions
• ProPublica's COMPAS Data Revisited
• Learning Fair and Interpretable Representations via Linear Orthogonalization
• Inherent Trade-offs in the Fair Allocation of Treatments
• Adversarial Regression with Doubly Non-negative Weighting Matrices
• The invisible power of fairness. How machine learning shapes democracy
• On the Identification of Fair Auditors to Evaluate Recommender Systems based on a Novel Non-Comparative Fairness Notion
• Fairness Preferences, Actual and Hypothetical: A Study of Crowdworker Incentives
• A Sociotechnical View of Algorithmic Fairness
• Non-Comparative Fairness for Human-Auditing and Its Relation to Traditional Fairness Notions