English

Multi-Community Spectral Clustering for Geometric Graphs

Social and Information Networks 2025-08-05 v1 Machine Learning Probability Spectral Theory Machine Learning

Abstract

In this paper, we consider the soft geometric block model (SGBM) with a fixed number k2k \geq 2 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 Rk1\mathbb{R}^{k-1} using the eigenvectors associated with the k1k-1 eigenvalues of the adjacency matrix of the graph that are closest to a value determined by the parameters of the model. It then applies kk-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.

Keywords

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}
}
R2 v1 2026-07-01T04:29:56.963Z