Fundamental limits of community detection from multi-view data: Multi-layer, dynamic and partially labeled block models

This is the authors' abstract. We don't add key points for this paper.

Multi-view data arises frequently in modern network analysis for example, relations of multiple types among individuals in social network analysis, longitudinal measurements of interactions among observational units, annotated networks with noisy partial labeling of vertices etc. We study community detection in these disparate settings via a unified theoretical framework, and investigate the fundamental thresholds for community recovery. We characterize the mutual information between the data and the latent parameters, provided the degrees are sufficiently large. Based on this general result, (i) we derive a sharp threshold for community detection in an inhomogeneous multi-layer block model (Ann. Statist. 50 (2022) 2664–2693), (ii) characterize a sharp threshold for weak recovery in a dynamic stochastic block model (J. R. Stat. Soc. Ser. B. Stat. Methodol. 79 (2017) 1119–1141), and (iii) identify the limiting mutual information in an unbalanced partially labeled block model. Finally, we introduce iterative algorithms based on Approximate Message Passing for community detection in these problems.