Optimal community detection in dense bipartite graphs

TL;DR

This paper establishes fundamental limits and proposes optimal tests for detecting dense bipartite communities in high-dimensional graphs, providing non-asymptotic bounds and novel statistical methods.

Contribution

It introduces non-asymptotic bounds on signal strength for community detection and develops minimax-optimal tests using nonlinear adjacency matrix statistics.

Findings

Derived matching upper and lower bounds for detection thresholds

Proposed minimax-optimal detection tests for dense bipartite communities

Analyzed nonlinear statistics of the adjacency matrix for community detection

Abstract

We consider the problem of detecting a community of densely connected vertices in a high-dimensional bipartite graph of size $n_1 \times n_2$. Under the null hypothesis, the observed graph is drawn from a bipartite Erd\H{o}s-Renyi distribution with connection probability $p_0$. Under the alternative hypothesis, there exists an unknown bipartite subgraph of size $k_1 \times k_2$ in which edges appear with probability $p_1 = p_0 + \delta$ for some $\delta > 0$, while all other edges outside the subgraph appear with probability $p_0$. Specifically, we provide non-asymptotic upper and lower bounds on the smallest signal strength $\delta^*$ that is both necessary and sufficient to ensure the existence of a test with small enough type one and type two errors. We also derive novel minimax-optimal tests achieving these fundamental limits when the underlying graph is sufficiently dense. Our proposed tests involve a combination of hard-thresholded nonlinear statistics of the adjacency matrix, the analysis of which may be of independent interest. In contrast with previous work, our non-asymptotic upper and lower bounds match for any configuration of $n_1,n_2, k_1,k_2$.