Density Evolution in the Degree-correlated Stochastic Block Model

Abstract

There is a recent surge of interest in identifying the sharp recovery thresholds for cluster recovery under the stochastic block model. In this paper, we address the more refined question of how many vertices that will be misclassified on average. We consider the binary form of the stochastic block model, where $n$ vertices are partitioned into two clusters with edge probability $a/n$ within the first cluster, $c/n$ within the second cluster, and $b/n$ across clusters. Suppose that as $n\to \infty$, $a=b+\mu \sqrt{b}$, $c=b+\nu \sqrt{b}$ for two fixed constants $\mu ,\nu$, and $b\to \infty$ with $b=n^{o(1)}$. When the cluster sizes are balanced and $\mu \ne \nu$, we show that the minimum fraction of misclassified vertices on average is given by $Q(\sqrt{v^{\ast }})$, where $Q(x)$ is the Q-function for standard normal, $v^{\ast }$ is the unique fixed point of $v=\frac{(\mu -\nu {)}^2}{16}+\frac{(\mu +\nu {)}^2}{16}\mathbb{E}[\tanh (v+\sqrt{v}Z)],$ and $Z$ is standard normal. Moreover, the minimum misclassified fraction on average is attained by a local algorithm, namely belief propagation, in time linear in the number of edges. Our proof techniques are based on connecting the cluster recovery problem to tree reconstruction problems, and analyzing the density evolution of belief propagation on trees with Gaussian approximations.

References in corpus (8)

• Phase transition in the detection of modules in sparse networks
• Community detection in general stochastic block models: fundamental limits and efficient recovery algorithms
• Accurate Community Detection in the Stochastic Block Model via Spectral Algorithms
• Achieving Optimal Misclassification Proportion in Stochastic Block Model
• Community detection in networks with unequal groups
• Achieving Exact Cluster Recovery Threshold via Semidefinite Programming: Extensions
• Asymptotic Mutual Information for the Two-Groups Stochastic Block Model
• Achieving Exact Cluster Recovery Threshold via Semidefinite Programming

Cited by in corpus (7)

• A Survey on Theoretical Advances of Community Detection in Networks
• Community Detection with Side Information: Exact Recovery under the Stochastic Block Model
• MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
• Community Recovery in Graphs with Locality
• Optimal Cluster Recovery in the Labeled Stochastic Block Model
• Matrix Completion with Hierarchical Graph Side Information
• Recovering a Hidden Community Beyond the Kesten-Stigum Threshold in $O(|E|{\log }^{\ast }|V|)$ Time