Analysis of Semi-Supervised Learning on Hypergraphs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Weihs, Adrien, Bertozzi, Andrea L., Thorpe, Matthew
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914169165447168
author Weihs, Adrien
Bertozzi, Andrea L.
Thorpe, Matthew
author_facet Weihs, Adrien
Bertozzi, Andrea L.
Thorpe, Matthew
contents Hypergraphs provide a natural framework for modeling higher-order interactions, yet their theoretical underpinnings in semi-supervised learning remain limited. We provide an asymptotic consistency analysis of variational learning on random geometric hypergraphs, precisely characterizing the conditions ensuring the well-posedness of hypergraph learning as well as showing convergence to a weighted $p$-Laplacian equation. Motivated by this, we propose Higher-Order Hypergraph Learning (HOHL), which regularizes via powers of Laplacians from skeleton graphs for multiscale smoothness. HOHL converges to a higher-order Sobolev seminorm. Empirically, it performs strongly on standard baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25354
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Analysis of Semi-Supervised Learning on Hypergraphs
Weihs, Adrien
Bertozzi, Andrea L.
Thorpe, Matthew
Machine Learning
Statistics Theory
Hypergraphs provide a natural framework for modeling higher-order interactions, yet their theoretical underpinnings in semi-supervised learning remain limited. We provide an asymptotic consistency analysis of variational learning on random geometric hypergraphs, precisely characterizing the conditions ensuring the well-posedness of hypergraph learning as well as showing convergence to a weighted $p$-Laplacian equation. Motivated by this, we propose Higher-Order Hypergraph Learning (HOHL), which regularizes via powers of Laplacians from skeleton graphs for multiscale smoothness. HOHL converges to a higher-order Sobolev seminorm. Empirically, it performs strongly on standard baselines.
title Analysis of Semi-Supervised Learning on Hypergraphs
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2510.25354