HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

Abstract

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obvious existence of such complex relationships in many real-world networks naturaly motivates the problem of learning with hypergraphs. A popular learning paradigm is hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabeled vertices in a hypergraph. Motivated by the fact that a graph convolutional network (GCN) has been effective for graph-based SSL, we propose HyperGCN, a novel GCN for SSL on attributed hypergraphs. Additionally, we show how HyperGCN can be used as a learning-based approach for combinatorial optimisation on NP-hard hypergraph problems. We demonstrate HyperGCN's effectiveness through detailed experimentation on real-world hypergraphs.

References in corpus (12)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Message Passing for Quantum Chemistry
• Discrete Signal Processing on Graphs
• Deep Convolutional Networks on Graph-Structured Data
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• Adversarial Attack and Defense on Graph Data: A Survey
• The Total Variation on Hypergraphs - Learning on Hypergraphs Revisited
• Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
• Dual-Primal Graph Convolutional Networks
• Confidence-based Graph Convolutional Networks for Semi-Supervised Learning
• Quadratic Decomposable Submodular Function Minimization
• Approximate k-Cover in Hypergraphs: Efficient Algorithms, and Applications

Cited by in corpus (18)

• Adversarial Attack and Defense on Graph Data: A Survey
• Signal Processing on Higher-Order Networks: Livin' on the Edge ... and Beyond
• Interpreting Deep Learning-Based Networking Systems
• Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• ConsRec: Learning Consensus Behind Interactions for Group Recommendation
• UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification
• Visual Analytics for Temporal Hypergraph Model Exploration
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation
• Higher-Order Networks Representation and Learning: A Survey
• Hypergraph Convolutional Network based Weakly Supervised Point Cloud Semantic Segmentation with Scene-Level Annotations
• Knowledge Hypergraph Embedding Meets Relational Algebra
• Hypergraph Learning based Recommender System for Anomaly Detection, Control and Optimization
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Strongly local p-norm-cut algorithms for semi-supervised learning and local graph clustering
• Stability and Generalization of Hypergraph Collaborative Networks
• Hypergraph $p$-Laplacian regularization on point clouds for data interpolation