Multi-Group Proportional Representation in Retrieval

TL;DR

This paper introduces Multi-Group Proportional Representation (MPR), a new metric for fairer image retrieval that accounts for intersectional identities, with algorithms to optimize it and evidence of improved fairness without sacrificing accuracy.

Contribution

The paper proposes MPR as a novel metric for intersectional fairness in retrieval, along with estimation methods, theoretical guarantees, and optimization algorithms to promote fairer representation.

Findings

Existing methods may fail to promote true intersectional fairness.

Optimizing MPR improves proportional representation across intersectional groups.

Achieves fairness with minimal impact on retrieval accuracy.

Abstract

Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attributes. However, most existing methods overlook intersectional groups determined by combinations of group attributes, such as gender, race, and ethnicity. We introduce Multi-Group Proportional Representation (MPR), a novel metric that measures representation across intersectional groups. We develop practical methods for estimating MPR, provide theoretical guarantees, and propose optimization algorithms to ensure MPR in retrieval. We demonstrate that existing methods optimizing for equal and proportional representation metrics may fail to promote MPR. Crucially, our work shows that optimizing MPR yields more proportional representation across multiple intersectional groups specified by a rich function class, often with minimal compromise in retrieval accuracy.