![Counting Complexity and Phase Transitions_hi-res logo](/sites/default/files/styles/workshop_banner_sm_1x/public/2023-01/Counting%20Complexity%20and%20Phase%20Transitions_hi-res.jpg?h=bf33d09a&itok=MrH5eN5T)
Abstract
Community detection consists in identification of groups of similar items within a population. In the context of online social networks, it is a useful primitive for recommending either contacts or news items to users. We will consider a particular generative probabilistic model for the observations, namely the so-called stochastic block model and prove that the non-backtracking operator provides a significant improvement when used for spectral clustering.