Open Access
Translator Disclaimer
2022 Sparse and smooth: Improved guarantees for spectral clustering in the dynamic stochastic block model
Nicolas Keriven, Samuel Vaiter
Author Affiliations +
Electron. J. Statist. 16(1): 1330-1366 (2022). DOI: 10.1214/22-EJS1986

Abstract

In this paper, we analyze classical variants of the Spectral Clustering (SC) algorithm in the Dynamic Stochastic Block Model (DSBM). Existing results show that, in the relatively sparse case where the expected degree grows logarithmically with the number of nodes, guarantees in the static case can be extended to the dynamic case and yield improved error bounds when the DSBM is sufficiently smooth in time, that is, the communities do not change too much between two time steps. We improve over these results by drawing a new link between the sparsity and the smoothness of the DSBM: the smoother the DSBM is, the more sparse it can be, while still guaranteeing consistent recovery. In particular, a mild condition on the smoothness allows to treat the sparse case with bounded degree. These guarantees are valid for the SC applied to the adjacency matrix or the normalized Laplacian. As a by-product of our analysis, we obtain to our knowledge the best spectral concentration bound available for the normalized Laplacian of matrices with independent Bernoulli entries.

Funding Statement

S. Vaiter was supported by ANR GraVa ANR-18-CE40-0005 and Projet ANER RAGA G048CVCRB-2018ZZ. N. Keriven was supported by ANR GRandMa ANR-21-CE23-0006.

Acknowledgments

We thank Nicolas Verzelen for useful discussion and pointing us to many references.

Citation

Download Citation

Nicolas Keriven. Samuel Vaiter. "Sparse and smooth: Improved guarantees for spectral clustering in the dynamic stochastic block model." Electron. J. Statist. 16 (1) 1330 - 1366, 2022. https://doi.org/10.1214/22-EJS1986

Information

Received: 1 November 2020; Published: 2022
First available in Project Euclid: 2 March 2022

Digital Object Identifier: 10.1214/22-EJS1986

Keywords: Concentration bounds , dynamic network , dynamic stochastic block model , spectral clustering

JOURNAL ARTICLE
37 PAGES


SHARE
Vol.16 • No. 1 • 2022
Back to Top