Proportionally Fair Clustering

TL;DR

This paper introduces a new fairness criterion called proportionality for clustering, ensuring no subset of points prefers their own cluster over existing centers, and provides algorithms to compute and evaluate such solutions.

Contribution

It formalizes proportional fairness in clustering, develops algorithms for finding and auditing these solutions, and analyzes the tradeoff with traditional k-means clustering.

Findings

Proposed algorithms efficiently compute proportional clustering solutions.

Empirical analysis shows tradeoff between fairness and clustering quality.

Demonstrated the practicality of proportional fairness in real datasets.

Abstract

We extend the fair machine learning literature by considering the problem of proportional centroid clustering in a metric context. For clustering $n$ points with $k$ centers, we define fairness as proportionality to mean that any $n/k$ points are entitled to form their own cluster if there is another center that is closer in distance for all $n/k$ points. We seek clustering solutions to which there are no such justified complaints from any subsets of agents, without assuming any a priori notion of protected subsets. We present and analyze algorithms to efficiently compute, optimize, and audit proportional solutions. We conclude with an empirical examination of the tradeoff between proportional solutions and the $k$-means objective.