Within-group fairness: A guidance for more sound between-group fairness

TL;DR

This paper introduces the concept of within-group fairness in AI, emphasizing the importance of fairness not only between different sensitive groups but also within the same group, and proposes algorithms to achieve this.

Contribution

It defines within-group fairness, develops mathematical formulations, and proposes algorithms to ensure fairness both within and between sensitive groups.

Findings

Algorithms improve within-group fairness without losing accuracy.

Proposed methods enhance between-group fairness as well.

Numerical studies validate the effectiveness of the algorithms.

Abstract

As they have a vital effect on social decision-making, AI algorithms not only should be accurate and but also should not pose unfairness against certain sensitive groups (e.g., non-white, women). Various specially designed AI algorithms to ensure trained AI models to be fair between sensitive groups have been developed. In this paper, we raise a new issue that between-group fair AI models could treat individuals in a same sensitive group unfairly. We introduce a new concept of fairness so-called within-group fairness which requires that AI models should be fair for those in a same sensitive group as well as those in different sensitive groups. We materialize the concept of within-group fairness by proposing corresponding mathematical definitions and developing learning algorithms to control within-group fairness and between-group fairness simultaneously. Numerical studies show that the proposed learning algorithms improve within-group fairness without sacrificing accuracy as well as between-group fairness.