Information-theoretic thresholds for community detection in sparse networks

TL;DR

This paper establishes precise bounds on the information-theoretic threshold for community detection in sparse stochastic block models, identifying when detection is statistically possible or impossible based on network parameters.

Contribution

It provides new upper and lower bounds on the detection threshold, including tight results for large numbers of communities and different regimes of community strength.

Findings

Detection is possible above the threshold with an exponential-time algorithm.

Below the threshold, no algorithm can outperform chance in labeling nodes.

The threshold scales as ( rac{\, ext{log} k}{k \, ext{lambda}^2}) for large k.

Abstract

We give upper and lower bounds on the information-theoretic threshold for community detection in the stochastic block model. Specifically, let $k$ be the number of groups, $d$ be the average degree, the probability of edges between vertices within and between groups be $c_\mathrm{in}/n$ and $c_\mathrm{out}/n$ respectively, and let $\lambda = (c_\mathrm{in}-c_\mathrm{out})/(kd)$. We show that, when $k$ is large, and $\lambda = O(1/k)$, the critical value of $d$ at which community detection becomes possible -- in physical terms, the condensation threshold -- is \[ d_c = \Theta\!\left( \frac{\log k}{k \lambda^2} \right) \, , \] with tighter results in certain regimes. Above this threshold, we show that the only partitions of the nodes into $k$ groups are correlated with the ground truth, giving an exponential-time algorithm that performs better than chance -- in particular, detection is possible for $k \ge 5$ in the disassortative case $\lambda < 0$ and for $k \ge 11$ in the assortative case $\lambda > 0$. (Similar upper bounds were obtained independently by Abbe and Sandon.) Below this threshold, we use recent results of Neeman and Netrapalli (who generalized arguments of Mossel, Neeman, and Sly) to show that no algorithm can label the vertices better than chance, or even distinguish the block model from an Erd\H{o}s-R\'enyi random graph with high probability. We also rely on bounds on certain functions of doubly stochastic matrices due to Achlioptas and Naor; indeed, our lower bound on $d_c$ is the second moment lower bound on the $k$-colorability threshold for random graphs with a certain effective degree.