Saved in:
Bibliographic Details
Main Authors: Dreveton, Maximilien, Liu, Elaine Siyu, Grossglauser, Matthias, Thiran, Patrick
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.21669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918170073235456
author Dreveton, Maximilien
Liu, Elaine Siyu
Grossglauser, Matthias
Thiran, Patrick
author_facet Dreveton, Maximilien
Liu, Elaine Siyu
Grossglauser, Matthias
Thiran, Patrick
contents This paper establishes the theoretical limits of graph clustering under the Popularity-Adjusted Block Model (PABM), addressing limitations of existing models. In contrast to the Stochastic Block Model (SBM), which assumes uniform vertex degrees, and to the Degree-Corrected Block Model (DCBM), which applies uniform degree corrections across clusters, PABM introduces separate popularity parameters for intra- and inter-cluster connections. Our main contribution is the characterization of the optimal error rate for clustering under PABM, which provides novel insights on clustering hardness: we demonstrate that unlike SBM and DCBM, cluster recovery remains possible in PABM even when traditional edge-density signals vanish, provided intra- and inter-cluster popularity coefficients differ. This highlights a dimension of degree heterogeneity captured by PABM but overlooked by DCBM: local differences in connectivity patterns can enhance cluster separability independently of global edge densities. Finally, because PABM exhibits a richer structure, its expected adjacency matrix has rank between $k$ and $k^2$, where $k$ is the number of clusters. As a result, spectral embeddings based on the top $k$ eigenvectors may fail to capture important structural information. Our numerical experiments on both synthetic and real datasets confirm that spectral clustering algorithms incorporating $k^2$ eigenvectors outperform traditional spectral approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21669
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimal Graph Clustering without Edge Density Signals
Dreveton, Maximilien
Liu, Elaine Siyu
Grossglauser, Matthias
Thiran, Patrick
Machine Learning
This paper establishes the theoretical limits of graph clustering under the Popularity-Adjusted Block Model (PABM), addressing limitations of existing models. In contrast to the Stochastic Block Model (SBM), which assumes uniform vertex degrees, and to the Degree-Corrected Block Model (DCBM), which applies uniform degree corrections across clusters, PABM introduces separate popularity parameters for intra- and inter-cluster connections. Our main contribution is the characterization of the optimal error rate for clustering under PABM, which provides novel insights on clustering hardness: we demonstrate that unlike SBM and DCBM, cluster recovery remains possible in PABM even when traditional edge-density signals vanish, provided intra- and inter-cluster popularity coefficients differ. This highlights a dimension of degree heterogeneity captured by PABM but overlooked by DCBM: local differences in connectivity patterns can enhance cluster separability independently of global edge densities. Finally, because PABM exhibits a richer structure, its expected adjacency matrix has rank between $k$ and $k^2$, where $k$ is the number of clusters. As a result, spectral embeddings based on the top $k$ eigenvectors may fail to capture important structural information. Our numerical experiments on both synthetic and real datasets confirm that spectral clustering algorithms incorporating $k^2$ eigenvectors outperform traditional spectral approaches.
title Optimal Graph Clustering without Edge Density Signals
topic Machine Learning
url https://arxiv.org/abs/2510.21669