A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges
It provides a comprehensive overview for researchers and practitioners working on fairness in ML, but it is incremental as it synthesizes existing work rather than introducing novel methods.
This survey addresses the problem of intersectional bias in machine learning, which involves multiple sensitive attributes like race and gender, by reviewing state-of-the-art notions, mitigation techniques, and challenges, without presenting new experimental results.
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.