A Sub-4 Approximation for Fair $k$-Means

Abstract:Fairness in clustering has attracted sustained research interest, motivated by the need to ensure equitable representation of protected groups in machine learning applications. We study fair $k$-means clustering in Euclidean space, where the proportion of each protected group in every cluster must lie within specified lower and upper bounds. These constraints make it challenging to determine both cluster centers and point assignments. We propose an approximation algorithm that combines a linear programming relaxation with geometric transformations of the input to construct candidate center sets. Given a $\rho$-approximate algorithm for weighted $k$-means and any $\epsilon>0$, our algorithm returns a fractional solution whose cost is at most $1+(3-1/\Gamma)\rho+O(\epsilon)$ times the optimal integral fair cost, where $\Gamma\approx6.357$ is an upper bound on the integrality gap of the standard Euclidean $k$-means LP. With a PTAS as the subroutine, the approximation ratio becomes $3.8427+O(\epsilon)$, improving the previous factor of $5+O(\epsilon)$ to below $4$. The solution satisfies all fairness constraints exactly and can be rounded to an integral assignment with a bounded additive violation of fairness and no increase in cost. The same approximation guarantee extends to the $k$-sparse Wasserstein barycenter problem.

Computational Geometry (cs.CG); Machine Learning (cs.LG)

arXiv:2609.07974 [cs.CG]

(or arXiv:2609.07974v1 [cs.CG] for this version)

https://doi.org/10.48550/arXiv.2609.07974 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.