Review of Mathematical frameworks for Fairness in Machine Learning

2020/05/26 by Eustasio del Barrio, del Barrio, Eustasio, Paula Gordaliza +3 · 4 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2005.13755

openalex publication_date 2020/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

A review of the main fairness definitions and fair learning methodologies proposed in the literature over the last years is presented from a mathematical point of view. Following our independence-based approach, we consider how to build fair algorithms and the consequences on the degradation of their performance compared to the possibly unfair case. This corresponds to the price for fairness given by the criteria statistical parity or equality of odds. Novel results giving the expressions of the optimal fair classifier and the optimal fair predictor (under a linear regression gaussian model) in the sense of equality of odds are presented.

Citations

• Equality of Opportunity in Supervised Learning
• Learning Non-Discriminatory Predictors
• Fairness in Criminal Justice Risk Assessments: The State of the Art
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• From Parity to Preference-based Notions of Fairness in Classification
• Obtaining fairness using optimal transport theory
• Predict Responsibly: Improving Fairness and Accuracy by Learning to\n Defer

Cited by

• Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information
• Bias and Debias in Recommender System: A Survey and Future Directions
• Fairness with Continuous Optimal Transport
• Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone

Related

• Metrizing Fairness
• Accuracy and Fairness Trade-offs in Machine Learning: A Stochastic Multi-Objective Approach
• Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
• The Authority of "Fair" in Machine Learning
• Fairness and Randomness in Machine Learning: Statistical Independence and Relativization