Graph Community Detection from Coarse Measurements: Recovery Conditions for the Coarsened Weighted Stochastic Block Model

TL;DR

This paper investigates conditions under which community structures can be recovered from low-resolution, coarsened measurements of graphs modeled by the stochastic block model, providing theoretical guarantees for perfect recovery.

Contribution

It introduces a formal coarsening model for stochastic block graphs and derives explicit conditions for accurate community recovery from coarse measurements.

Findings

Derived error bounds for community recovery

Provided asymptotic conditions for perfect recovery

Formalized the coarsening process in stochastic block models

Abstract

We study the problem of community recovery from coarse measurements of a graph. In contrast to the problem of community recovery of a fully observed graph, one often encounters situations when measurements of a graph are made at low-resolution, each measurement integrating across multiple graph nodes. Such low-resolution measurements effectively induce a coarse graph with its own communities. Our objective is to develop conditions on the graph structure, the quantity, and properties of measurements, under which we can recover the community organization in this coarse graph. In this paper, we build on the stochastic block model by mathematically formalizing the coarsening process, and characterizing its impact on the community members and connections. Through this novel setup and modeling, we characterize an error bound for community recovery. The error bound yields simple and closed-form asymptotic conditions to achieve the perfect recovery of the coarse graph communities.