Perfect Clustering in Nonuniform Hypergraphs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chan, Ga-Ming Angus, Lubberts, Zachary
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910909683728384
author Chan, Ga-Ming Angus
Lubberts, Zachary
author_facet Chan, Ga-Ming Angus
Lubberts, Zachary
contents While there has been tremendous activity in the area of statistical network inference on graphs, hypergraphs have not enjoyed the same attention, on account of their relative complexity and the lack of tractable statistical models. We introduce a hyper-edge-centric model for analyzing hypergraphs, called the interaction hypergraph, which models natural sampling methods for hypergraphs in neuroscience and communication networks, and accommodates interactions involving different numbers of entities. We define latent embeddings for the interactions in such a network, and analyze their estimators. In particular, we show that a spectral estimate of the interaction latent positions can achieve perfect clustering once enough interactions are observed.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08980
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Perfect Clustering in Nonuniform Hypergraphs
Chan, Ga-Ming Angus
Lubberts, Zachary
Methodology
Statistics Theory
Machine Learning
05C65, 05C80, 60B20, 62F12
While there has been tremendous activity in the area of statistical network inference on graphs, hypergraphs have not enjoyed the same attention, on account of their relative complexity and the lack of tractable statistical models. We introduce a hyper-edge-centric model for analyzing hypergraphs, called the interaction hypergraph, which models natural sampling methods for hypergraphs in neuroscience and communication networks, and accommodates interactions involving different numbers of entities. We define latent embeddings for the interactions in such a network, and analyze their estimators. In particular, we show that a spectral estimate of the interaction latent positions can achieve perfect clustering once enough interactions are observed.
title Perfect Clustering in Nonuniform Hypergraphs
topic Methodology
Statistics Theory
Machine Learning
05C65, 05C80, 60B20, 62F12
url https://arxiv.org/abs/2504.08980