The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited

Abstract

Hypergraphs allow one to encode higher-order relationships in data and are thus a very flexible modeling tool. Current learning methods are either based on approximations of the hypergraphs via graphs or on tensor methods which are only applicable under special conditions. In this paper, we present a new learning framework on hypergraphs which fully uses the hypergraph structure. The key element is a family of regularization functionals based on the total variation on hypergraphs.

Long version of paper accepted at NIPS 2013

Cited by in corpus (31)

• Topological Signal Processing over Simplicial Complexes
• HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs
• Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond
• Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
• GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays
• Exact Recovery in the Hypergraph Stochastic Block Model: a Spectral Algorithm
• Learning on Hypergraphs with Sparsity
• $p$-Laplace Operators for Oriented Hypergraphs
• Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
• Revisiting Decomposable Submodular Function Minimization with Incidence Relations
• Local Hypergraph Clustering using Capacity Releasing Diffusion
• Strongly Local Hypergraph Diffusions for Clustering and Semi-supervised Learning
• Hypergraph $p$-Laplacian: A Differential Geometry View
• A Versatile Framework for Attributed Network Clustering via K-Nearest Neighbor Augmentation
• Hypergraph Modeling via Spectral Embedding Connection: Hypergraph Cut, Weighted Kernel $k$-means, and Heat Kernel
• Local Hyper-Flow Diffusion
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• Hypergraph $p$-Laplacian regularization on point clouds for data interpolation
• Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning
• Towards Tight Bounds for Spectral Sparsification of Hypergraphs
• Semi-Supervised Classification on Non-Sparse Graphs Using Low-Rank Graph Convolutional Networks
• Quadratic Decomposable Submodular Function Minimization: Theory and Practice (Computation and Analysis of PageRank over Hypergraphs)
• Parametric Maxflows for Structured Sparse Learning with Convex Relaxations of Submodular Functions
• Regularized Recovery by Multi-order Partial Hypergraph Total Variation
• A nonlinear diffusion method for semi-supervised learning on hypergraphs
• Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
• Semi-supervised Learning for Aggregated Multilayer Graphs Using Diffuse Interface Methods and Fast Matrix Vector Products
• Augmented Sparsifiers for Generalized Hypergraph Cuts with Applications to Decomposable Submodular Function Minimization
• Exact Partitioning of High-order Models with a Novel Convex Tensor Cone Relaxation