Exact Phase Transitions for Stochastic Block Models and Reconstruction on Trees

TL;DR

This paper rigorously establishes the exact phase transition thresholds for community detection in stochastic block models with 3 and 4 communities, confirming conjectures and analyzing the influence of average degree on detectability.

Contribution

It proves the absence of a computational-statistical gap above the Kesten-Stigum bound for q=3 and 4, and shows the bound's tightness depends on average degree, advancing understanding of phase transitions.

Findings

No detection below the Kesten-Stigum bound for q=3,4 with high average degree.

The Kesten-Stigum bound is not sharp for q≥5.

Reconstruction on Galton-Watson trees is impossible under certain conditions.

Abstract

In this paper we continue to rigorously establish the predictions in ground breaking work in statistical physics by Decelle, Krzakala, Moore, Zdeborov\'a (2011) regarding the block model, in particular in the case of $q=3$ and $q=4$ communities. We prove that for $q=3$ and $q=4$ there is no computational-statistical gap if the average degree is above some constant by showing it is information theoretically impossible to detect below the Kesten-Stigum bound. The proof is based on showing that for the broadcast process on Galton-Watson trees, reconstruction is impossible for $q=3$ and $q=4$ if the average degree is sufficiently large. This improves on the result of Sly (2009), who proved similar results for regular trees for $q=3$. Our analysis of the critical case $q=4$ provides a detailed picture showing that the tightness of the Kesten-Stigum bound in the antiferromagnetic case depends on the average degree of the tree. We also prove that for $q\geq 5$, the Kestin-Stigum bound is not sharp. Our results prove conjectures of Decelle, Krzakala, Moore, Zdeborov\'a (2011), Moore (2017), Abbe and Sandon (2018) and Ricci-Tersenghi, Semerjian, and Zdeborov\'a (2019). Our proofs are based on a new general coupling of the tree and graph processes and on a refined analysis of the broadcast process on the tree.