English

Optimal Bipartite Network Clustering

Statistics Theory 2018-12-27 v2 Social and Information Networks Machine Learning Statistics Theory

Abstract

We study bipartite community detection in networks, or more generally the network biclustering problem. We present a fast two-stage procedure based on spectral initialization followed by the application of a pseudo-likelihood classifier twice. Under mild regularity conditions, we establish the weak consistency of the procedure (i.e., the convergence of the misclassification rate to zero) under a general bipartite stochastic block model. We show that the procedure is optimal in the sense that it achieves the optimal convergence rate that is achievable by a biclustering oracle, adaptively over the whole class, up to constants. This is further formalized by deriving a minimax lower bound over a class of biclustering problems. The optimal rate we obtain sharpens some of the existing results and generalizes others to a wide regime of average degree growth, from sparse networks with average degrees growing arbitrarily slowly to fairly dense networks with average degrees of order n\sqrt{n}. As a special case, we recover the known exact recovery threshold in the logn\log n regime of sparsity. To obtain the consistency result, as part of the provable version of the algorithm, we introduce a sub-block partitioning scheme that is also computationally attractive, allowing for distributed implementation of the algorithm without sacrificing optimality. The provable algorithm is derived from a general class of pseudo-likelihood biclustering algorithms that employ simple EM type updates. We show the effectiveness of this general class by numerical simulations.

Keywords

Cite

@article{arxiv.1803.06031,
  title  = {Optimal Bipartite Network Clustering},
  author = {Zhixin Zhou and Arash A. Amini},
  journal= {arXiv preprint arXiv:1803.06031},
  year   = {2018}
}
R2 v1 2026-06-23T00:54:57.820Z