Work

Consistency of spectral clustering in stochastic block models

Year: 2014
Type: article
Abstract: We analyze the performance of spectral clustering for community extraction in stochastic block models. We show that, under mild conditions, spectral clustering applied to the adjacency matrix of the network can consistently recover hidden communities even when the order of the maximum expected degree is as small as $\log n$, with $n$ the number of nodes. This result applies to some popular polynomial time spectral clustering algorithms and is further extended to degree corrected stochastic block models using a spherical $k$-median spectral clustering method. A key component of our analysis is a combinatorial bound on the spectrum of binary random matrices, which is sharper than the conventional matrix Bernstein inequality and may be of independent interest.
Authors: Jing Lei, Alessandro Rinaldo
Language: English
Open Access status: bronze
OpenAlex ID: W2051638434
FWCI: 7.373
Cites: 47
Cited by: 421
Related to: 10