Improved Analysis of Spectral Algorithm for Clustering

TL;DR

This paper improves theoretical guarantees for spectral clustering algorithms on well-clustered graphs by weakening assumptions and evaluating different spectral embedding maps, enhancing understanding of their success.

Contribution

It provides a better performance guarantee under weaker assumptions and compares different spectral embedding maps for clustering.

Findings

Improved performance guarantees under weaker graph assumptions

Evaluation of spectral embedding maps by Ng et al. (2001)

Enhanced understanding of spectral clustering success

Abstract

Spectral algorithms are graph partitioning algorithms that partition a node set of a graph into groups by using a spectral embedding map. Clustering techniques based on the algorithms are referred to as spectral clustering and are widely used in data analysis. To gain a better understanding of why spectral clustering is successful, Peng et al. (2015) and Kolev and Mehlhorn (2016) studied the behavior of a certain type of spectral algorithm for a class of graphs, called well-clustered graphs. Specifically, they put an assumption on graphs and showed the performance guarantee of the spectral algorithm under it. The algorithm they studied used the spectral embedding map developed by Shi and Malic (2000). In this paper, we improve on their results, giving a better performance guarantee under a weaker assumption. We also evaluate the performance of the spectral algorithm with the spectral embedding map developed by Ng et al. (2001).