The Annals of Statistics
- Ann. Statist.
- Volume 41, Number 4 (2013), 2097-2122.
Pseudo-likelihood methods for community detection in large sparse networks
Many algorithms have been proposed for fitting network models with communities, but most of them do not scale well to large networks, and often fail on sparse networks. Here we propose a new fast pseudo-likelihood method for fitting the stochastic block model for networks, as well as a variant that allows for an arbitrary degree distribution by conditioning on degrees. We show that the algorithms perform well under a range of settings, including on very sparse networks, and illustrate on the example of a network of political blogs. We also propose spectral clustering with perturbations, a method of independent interest, which works well on sparse networks where regular spectral clustering fails, and use it to provide an initial value for pseudo-likelihood. We prove that pseudo-likelihood provides consistent estimates of the communities under a mild condition on the starting value, for the case of a block model with two communities.
Ann. Statist., Volume 41, Number 4 (2013), 2097-2122.
First available in Project Euclid: 23 October 2013
Permanent link to this document
Digital Object Identifier
Mathematical Reviews number (MathSciNet)
Zentralblatt MATH identifier
Amini, Arash A.; Chen, Aiyou; Bickel, Peter J.; Levina, Elizaveta. Pseudo-likelihood methods for community detection in large sparse networks. Ann. Statist. 41 (2013), no. 4, 2097--2122. doi:10.1214/13-AOS1138. https://projecteuclid.org/euclid.aos/1382547514
- Supplementary material: Extension to unbalanced communities. This supplement contains an extension of Theorem 1 to the case of unbalanced communities.