English

Stochastic Block Model for Hypergraphs: Statistical limits and a semidefinite programming approach

Probability 2018-07-10 v1 Information Theory Machine Learning math.IT

Abstract

We study the problem of community detection in a random hypergraph model which we call the stochastic block model for kk-uniform hypergraphs (kk-SBM). We investigate the exact recovery problem in kk-SBM and show that a sharp phase transition occurs around a threshold: below the threshold it is impossible to recover the communities with non-vanishing probability, yet above the threshold there is an estimator which recovers the communities almost asymptotically surely. We also consider a simple, efficient algorithm for the exact recovery problem which is based on a semidefinite relaxation technique.

Keywords

Cite

@article{arxiv.1807.02884,
  title  = {Stochastic Block Model for Hypergraphs: Statistical limits and a semidefinite programming approach},
  author = {Chiheon Kim and Afonso S. Bandeira and Michel X. Goemans},
  journal= {arXiv preprint arXiv:1807.02884},
  year   = {2018}
}
R2 v1 2026-06-23T02:54:12.896Z