Stochastic Block Model
Overview
Stochastic block models study how to infer hidden communities from network edges, and provide a testbed for understanding when network structure is detectable. Common approaches include spectral and non-backtracking algorithms, belief propagation, likelihood-based inference, and extensions for directed, multilayer, temporal, or hypergraph data. Researchers evaluate these methods on sparse graphs and study tasks such as weak or exact recovery, estimating the number of communities, and using limited queries to improve labels. Recovery thresholds are understood in many settings, but an important tension remains between what is statistically possible and what efficient algorithms can achieve, especially near sparse-graph detection limits.
Latest papers
13 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.