Spectral Thresholds in the Bipartite Stochastic Block Model

TL;DR

This paper analyzes the thresholds for detecting and recovering planted partitions in bipartite stochastic block models, introducing a spectral algorithm that nearly optimally recovers the partition at minimal edge densities.

Contribution

It identifies sharp detection thresholds, characterizes phase transitions in spectral properties, and proposes a simple spectral algorithm with near-optimal performance.

Findings

Sharp detection threshold established

Spectral phase transition characterized

Proposed algorithm nearly optimal in edge density

Abstract

We consider a bipartite stochastic block model on vertex sets $V_1$ and $V_2$, with planted partitions in each, and ask at what densities efficient algorithms can recover the partition of the smaller vertex set. When $|V_2| \gg |V_1|$, multiple thresholds emerge. We first locate a sharp threshold for detection of the partition, in the sense of the results of \cite{mossel2012stochastic,mossel2013proof} and \cite{massoulie2014community} for the stochastic block model. We then show that at a higher edge density, the singular vectors of the rectangular biadjacency matrix exhibit a localization / delocalization phase transition, giving recovery above the threshold and no recovery below. Nevertheless, we propose a simple spectral algorithm, Diagonal Deletion SVD, which recovers the partition at a nearly optimal edge density. The bipartite stochastic block model studied here was used by \cite{feldman2014algorithm} to give a unified algorithm for recovering planted partitions and assignments in random hypergraphs and random $k$-SAT formulae respectively. Our results give the best known bounds for the clause density at which solutions can be found efficiently in these models as well as showing a barrier to further improvement via this reduction to the bipartite block model.