Exact Recovery in the Stochastic Block Model

TL;DR

This paper establishes a sharp threshold for exact community recovery in the stochastic block model, proposes an efficient semidefinite programming algorithm near this threshold, and improves upon previous bounds.

Contribution

It identifies the precise phase transition for exact recovery and introduces an efficient algorithm that approaches this theoretical limit.

Findings

Sharp threshold condition for exact recovery established

Semidefinite programming algorithm succeeds near the threshold

Numerical experiments suggest near-optimal performance

Abstract

The stochastic block model (SBM) with two communities, or equivalently the planted bisection model, is a popular model of random graph exhibiting a cluster behaviour. In the symmetric case, the graph has two equally sized clusters and vertices connect with probability $p$ within clusters and $q$ across clusters. In the past two decades, a large body of literature in statistics and computer science has focused on providing lower-bounds on the scaling of $|p-q|$ to ensure exact recovery. In this paper, we identify a sharp threshold phenomenon for exact recovery: if $\alpha=pn/\log(n)$ and $\beta=qn/\log(n)$ are constant (with $\alpha>\beta$), recovering the communities with high probability is possible if $\frac{\alpha+\beta}{2} - \sqrt{\alpha \beta}>1$ and impossible if $\frac{\alpha+\beta}{2} - \sqrt{\alpha \beta}<1$. In particular, this improves the existing bounds. This also sets a new line of sight for efficient clustering algorithms. While maximum likelihood (ML) achieves the optimal threshold (by definition), it is in the worst-case NP-hard. This paper proposes an efficient algorithm based on a semidefinite programming relaxation of ML, which is proved to succeed in recovering the communities close to the threshold, while numerical experiments suggest it may achieve the threshold. An efficient algorithm which succeeds all the way down to the threshold is also obtained using a partial recovery algorithm combined with a local improvement procedure.