Higher-Order Regularization Learning on Hypergraphs
Not on the map. Why?
Abstract (arXiv)
Higher-Order Hypergraph Learning (HOHL) was recently introduced as a principled alternative to classical hypergraph regularization, enforcing higher-order smoothness via powers of multiscale Laplacians induced by the hypergraph structure. Prior work established the well- and ill-posedness of HOHL through an asymptotic consistency analysis in geometric settings. We extend this theoretical foundation by proving the consistency of a truncated version of HOHL and deriving explicit convergence rates when HOHL is used as a regularizer in fully supervised learning. We further demonstrate its strong empirical performance in active learning and in datasets lacking an underlying geometric structure, highlighting HOHL's versatility and robustness across diverse learning settings.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 102 references that are in the map. First posted on arXiv 30 Oct 2025.
Builds on
43 of 102 references.
References · 43
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
- 2021Graph Learning: A Surveycited by 140
- 2022FoSR: First-order spectral rewiring for addressing oversquashing in GNNscited by 104
- 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 96
- 2018Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operatorcited by 70
- 2022On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networkscited by 63
- 2020Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Ratescited by 49
- 2019Random Walks on Hypergraphs with Edge-Dependent Vertex Weightscited by 45
- 2017Analysis of p-Laplacian Regularization in Semi-Supervised Learningcited by 39
- 2023Mitigating Over-Smoothing and Over-Squashing using Augmentations of Forman-Ricci Curvaturecited by 39
- 2013The Total Variation on Hypergraphs - Learning on Hypergraphs Revisitedcited by 35
31 more
- 2015A variational approach to the consistency of spectral clusteringcited by 28
- 2015A Survey of Signed Network Mining in Social Mediacited by 25
- 2018Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clusteringcited by 25
- 2014Continuum limit of total variation on point cloudscited by 24
- 2017The game theoretic p-Laplacian and semi-supervised learning with few labelscited by 22
- 2018Large Data and Zero Noise Limits of Graph-Based Semi-Supervised Learning Algorithmscited by 22
- 2020Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansioncited by 21
- 2013Spectral Convergence of the connection Laplacian from random samplescited by 19
- 2018Properly-weighted graph Laplacian for semi-supervised learningcited by 19
- 2020Rates of Convergence for Laplacian Semi-Supervised Learning with Low Labeling Ratescited by 18
- 2024A Survey of Data-Efficient Graph Learningcited by 18
- 2015Algorithms for Lipschitz Learning on Graphscited by 16
- 2017Consistency of Lipschitz learning with infinite unlabeled data and finite labeled datacited by 15
- 2017Hypergraph p-Laplacian: A Differential Geometry Viewcited by 11
- 2017A random matrix analysis and improvement of semi-supervised learning for large dimensional datacited by 10
- 2021Uniform Convergence Rates for Lipschitz Learning on Graphscited by 9
- 2021Model-Change Active Learning in Graph-Based Semi-Supervised Learningcited by 8
- 2014Consistency of Cheeger and Ratio Graph Cutscited by 6
- 2015Spectral Convergence Rate of Graph Laplaciancited by 6
- 2019Mumford-Shah functionals on graphs and their asymptoticscited by 6
- 2020From graph cuts to isoperimetric inequalities: Convergence rates of Cheeger cuts on data cloudscited by 6
- 2020Continuum Limit of Lipschitz Learning on Graphscited by 6
- 2023Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observationscited by 6
- 2021Multiscale Laplacian Learningcited by 5
- 2016A new analytical approach to consistency and overfitting in regularized empirical risk minimizationcited by 4
- 2022Rates of Convergence for Regression with the Graph Poly-Laplaciancited by 4
- 2021Consensus Dynamics and Opinion Formation on Hypergraphscited by 3
- 2024Convergence rates for Poisson learning to a Poisson equation with measure datacited by 3
- 2017Consistency of Dirichlet Partitionscited by 2
- 2024Hypergraph p-Laplacian equations for data interpolation and semi-supervised learningcited by 1
- 2025Analysis of Semi-Supervised Learning on Hypergraphscited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.