A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges

TL;DR

This survey reviews the current state of intersectional fairness in machine learning, discussing notions, mitigation strategies, and challenges related to biases involving multiple sensitive attributes.

Contribution

It provides a comprehensive taxonomy of intersectional fairness notions and mitigation methods, highlighting key challenges and guiding future research directions.

Findings

Identifies multiple intersectional bias types in machine learning.

Summarizes existing fairness mitigation techniques for intersectional attributes.

Outlines key challenges and future research directions in intersectional fairness.

Abstract

The widespread adoption of Machine Learning systems, especially in more decision-critical applications such as criminal sentencing and bank loans, has led to increased concerns about fairness implications. Algorithms and metrics have been developed to mitigate and measure these discriminations. More recently, works have identified a more challenging form of bias called intersectional bias, which encompasses multiple sensitive attributes, such as race and gender, together. In this survey, we review the state-of-the-art in intersectional fairness. We present a taxonomy for intersectional notions of fairness and mitigation. Finally, we identify the key challenges and provide researchers with guidelines for future directions.