Non-Convex Exact Community Recovery in Stochastic Block Model

Abstract

Community detection in graphs that are generated according to stochastic block models (SBMs) has received much attention lately. In this paper, we focus on the binary symmetric SBM -- in which a graph of $n$ vertices is randomly generated by first partitioning the vertices into two equal-sized communities and then connecting each pair of vertices with probability that depends on their community memberships -- and study the associated exact community recovery problem. Although the maximum-likelihood formulation of the problem is non-convex and discrete, we propose to tackle it using a popular iterative method called projected power iterations. To ensure fast convergence of the method, we initialize it using a point that is generated by another iterative method called orthogonal iterations, which is a classic method for computing invariant subspaces of a symmetric matrix. We show that in the logarithmic sparsity regime of the problem, with high probability the proposed two-stage method can exactly recover the two communities down to the information-theoretic limit in $\mathcal{O}(n{\log }^{2}n/\log \log n)$ time, which is competitive with a host of existing state-of-the-art methods that have the same recovery performance. We also conduct numerical experiments on both synthetic and real data sets to demonstrate the efficacy of our proposed method and complement our theoretical development.

arXiv commentA preliminary version of this work has appeared in the Proceedings of the 37th International Conference on Machine Learning (ICML 2020). This version is accepted for publication in Mathematical Programming

References in corpus (11)

• Community structure in social and biological networks
• Finding and evaluating community structure in networks
• Community detection in graphs
• Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Global rates of convergence for nonconvex optimization on manifolds
• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
• Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
• Near-optimal bounds for phase synchronization
• On the low-rank approach for semidefinite programs arising in synchronization and community detection
• The Global Landscape of Neural Networks: An Overview