Consistent Adjacency-Spectral Partitioning for the Stochastic Block Model When the Model Parameters Are Unknown

Abstract

For random graphs distributed according to a stochastic block model, we consider the inferential task of partitioning vertices into blocks using spectral techniques. Spectral partitioning using the normalized Laplacian and the adjacency matrix have both been shown to be consistent as the number of vertices tend to infinity. Importantly, both procedures require that the number of blocks and the rank of the communication probability matrix be known, even as the rest of the parameters may be unknown. In this paper, we prove that the (suitably modified) adjacency-spectral partitioning procedure, requiring only an upper bound on the rank of the communication probability matrix, is consistent. Indeed, this result demonstrates a robustness to model mis-specification; an overestimate of the rank may impose a moderate performance penalty, but the procedure is still consistent. Furthermore, we extend this procedure to the setting where adjacencies may have multiple modalities and we allow for either directed or undirected graphs.

Publication
SIAM Journal on Matrix Analysis and Applications