Distributed k-Means and k-Median Clustering on General Topologies

TL;DR

This paper introduces new distributed algorithms for k-means and k-median clustering that reduce communication costs and work on general network topologies, with proven guarantees and superior experimental performance.

Contribution

It presents a distributed coreset construction method for clustering that improves communication efficiency and applies to arbitrary topologies, advancing distributed clustering techniques.

Findings

Reduces communication complexity compared to previous methods.

Works effectively over general communication topologies.

Outperforms existing coreset-based distributed clustering algorithms in experiments.

Abstract

This paper provides new algorithms for distributed clustering for two popular center-based objectives, k-median and k-means. These algorithms have provable guarantees and improve communication complexity over existing approaches. Following a classic approach in clustering by \cite{har2004coresets}, we reduce the problem of finding a clustering with low cost to the problem of finding a coreset of small size. We provide a distributed method for constructing a global coreset which improves over the previous methods by reducing the communication complexity, and which works over general communication topologies. Experimental results on large scale data sets show that this approach outperforms other coreset-based distributed clustering algorithms.