English

Multilayer hypergraph clustering using the aggregate similarity matrix

Statistics Theory 2023-11-06 v3 Information Theory math.IT Probability Machine Learning Statistics Theory

Abstract

We consider the community recovery problem on a multilayer variant of the hypergraph stochastic block model (HSBM). Each layer is associated with an independent realization of a d-uniform HSBM on N vertices. Given the similarity matrix containing the aggregated number of hyperedges incident to each pair of vertices, the goal is to obtain a partition of the N vertices into disjoint communities. In this work, we investigate a semidefinite programming (SDP) approach and obtain information-theoretic conditions on the model parameters that guarantee exact recovery both in the assortative and the disassortative cases.

Keywords

Cite

@article{arxiv.2301.11657,
  title  = {Multilayer hypergraph clustering using the aggregate similarity matrix},
  author = {Kalle Alaluusua and Konstantin Avrachenkov and B. R. Vinay Kumar and Lasse Leskelä},
  journal= {arXiv preprint arXiv:2301.11657},
  year   = {2023}
}

Comments

16 pages, 3 tables. Reason for replacement on 3 Nov 2023: incorporating the possibility of non-uniform layers. Reason for replacement on 18 May 2023: improving clarity of the presentation and clarifying the contribution/novelty of the paper

R2 v1 2026-06-28T08:23:06.465Z