The cost of fairness in classification

2017/05/25 by Aditya Krishna Menon, Menon, Aditya Krishna, Robert C. Williamson +1 · 1 citation
Computer Science · Medicine · Social Sciences · #Ethics in Clinical Research #European and International Law Studies #FOS: Computer and information sciences #Law, AI, and Intellectual Property #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1705.09055

openalex publication_date 2017/05/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We study the problem of learning classifiers with a fairness constraint, with three main contributions towards the goal of quantifying the problem's inherent tradeoffs. First, we relate two existing fairness measures to cost-sensitive risks. Second, we show that for cost-sensitive classification and fairness measures, the optimal classifier is an instance-dependent thresholding of the class-probability function. Third, we show how the tradeoff between accuracy and fairness is determined by the alignment between the class-probabilities for the target and sensitive features. Underpinning our analysis is a general framework that casts the problem of learning with a fairness requirement as one of minimising the difference of two statistical risks.

Cited by

• Beyond Accuracy: Rethinking Hallucination and Regulatory Response in Generative AI

Related

• Empirical Risk Minimization under Fairness Constraints
• Accuracy vs. Accuracy: Computational Tradeoffs Between Classification Rates and Utility
• Optimal Transport of Classifiers to Fairness
• A Reductions Approach to Fair Classification
• Consider the Alternatives: Navigating Fairness-Accuracy Tradeoffs via Disqualification