Multi-Community Spectral Clustering for Geometric Graphs
Abstract
In this paper, we consider the soft geometric block model (SGBM) with a fixed number of homogeneous communities in the dense regime, and we introduce a spectral clustering algorithm for community recovery on graphs generated by this model. Given such a graph, the algorithm produces an embedding into using the eigenvectors associated with the eigenvalues of the adjacency matrix of the graph that are closest to a value determined by the parameters of the model. It then applies -means clustering to the embedding. We prove weak consistency and show that a simple local refinement step ensures strong consistency. A key ingredient is an application of a non-standard version of Davis-Kahan theorem to control eigenspace perturbations when eigenvalues are not simple. We also analyze the limiting spectrum of the adjacency matrix, using a combination of combinatorial and matrix techniques.
Cite
@article{arxiv.2508.00893,
title = {Multi-Community Spectral Clustering for Geometric Graphs},
author = {Luiz Emilio Allem and Konstantin Avrachenkov and Carlos Hoppen and Hariprasad Manjunath and Lucas Siviero Sibemberg},
journal= {arXiv preprint arXiv:2508.00893},
year = {2025}
}