Partitioning Well-Clustered Graphs: Spectral Clustering Works!

Richard Peng, He Sun, Luca Zanetti

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper we study variants of the widely used spectral clustering that partitions a graph into $k$ clusters by (1) embedding the vertices of a graph into a low-dimensional space using the bottom eigenvectors of the Laplacian matrix and (2) grouping the embedded points into $k$ clusters via $k$-means algorithms. We show that, for a wide class of graphs, spectral clustering gives a good approximation of the optimal clustering. While this approach was proposed in the early 1990s and has comprehensive applications, prior to our work similar results were known only for graphs generated from stochastic models. We also give a nearly linear time algorithm for partitioning well-clustered graphs based on computing a matrix exponential and approximate nearest neighbor data structures.
Original languageEnglish
Pages (from-to)710-743
Number of pages34
JournalSIAM Journal on Computing
Volume46
Issue number2
DOIs
Publication statusPublished - 30 Mar 2017
EventConference on Learning Theory 2015 - University Pierre and Marie Curie, Paris, France
Duration: 3 Jul 20156 Jul 2015
http://www.learningtheory.org/colt2015/

Fingerprint

Dive into the research topics of 'Partitioning Well-Clustered Graphs: Spectral Clustering Works!'. Together they form a unique fingerprint.

Cite this