Spectral Detection on Sparse Hypergraphs - Archive ouverte HAL Access content directly
Conference Papers Year :

Spectral Detection on Sparse Hypergraphs

(1) , (2) , (2, 3) , (4)
1
2
3
4

Abstract

We consider the problem of the assignment of nodes into communities from a set of hyperedges, where every hyperedge is a noisy observation of the community assignment of the adjacent nodes. We focus in particular on the sparse regime where the number of edges is of the same order as the number of vertices. We propose a spectral method based on a generalization of the non-backtracking Hashimoto matrix into hypergraphs. We analyze its performance on a planted generative model and compare it with other spectral methods and with Bayesian belief propagation (which was conjectured to be asymptotically optimal for this model). We conclude that the proposed spectral method detects communities whenever belief propagation does, while having the important advantages to be simpler, entirely nonparametric, and to be able to learn the rule according to which the hyperedges were generated without prior information.
Fichier principal
Vignette du fichier
1507.04113v1.pdf (1.46 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

cea-01330412 , version 1 (10-06-2016)

Identifiers

Cite

Maria Chiara Angelini, Francesco Caltagirone, Florent Krzakala, Lenka Zdeborová. Spectral Detection on Sparse Hypergraphs. Allerton Conference 2015 : 53rd Annual Allerton Conference on Communication, Control, and Computing, Sep 2015, Monticello, United States. pp.66-73, ⟨10.1109/ALLERTON.2015.7446987⟩. ⟨cea-01330412⟩
426 View
223 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More