Analysis of Semi-Supervised Learning on Hypergraphs

2025/10/29 by Adrien Weihs, Andrea L. Bertozzi, Weihs, Adrien +3 · 2 citations
Computer Science · Mathematics · #cs.LG #math.ST #stat.TH

paper · pdf · doi:10.48550/arxiv.2510.25354

Abstract

Hypergraphs provide a natural framework for modeling multiway interactions. We analyze a class of variational semi-supervised learning problems posed on random geometric hypergraphs and establish asymptotic consistency in the large-data limit. In particular, we identify scaling regimes that ensure well-posedness--yielding nontrivial label propagation rather than collapse to a constant labeling--and show that discrete minimizers converge, in the continuum, to solutions of a density-weighted p-Laplacian equation. We also propose Higher-Order Hypergraph Learning (HOHL), a multiscale regularization scheme based on powers of Laplacians associated with hypergraph-induced subgraphs. For geometric point clouds, we analyze an efficient multiscale Laplacian surrogate for HOHL and prove convergence to a higher-order Sobolev-type seminorm. Numerical experiments on standard benchmarks support the practical utility of the resulting higher-order regularization.

Cited by

• Higher-Order Regularization Learning on Hypergraphs
• Topology-Aware Active Learning on Graphs

Related

• Higher-Order Regularization Learning on Hypergraphs
• Analysis and algorithms for ℓ_p-based semi-supervised learning on graphs
• Analysis of p-Laplacian Regularization in Semi-Supervised Learning
• Rates of Convergence for Laplacian Semi-Supervised Learning with Low Labeling Rates
• A nonlinear diffusion method for semi-supervised learning on hypergraphs