Hypergraph Convolution and Hypergraph Attention

Abstract

Recently, graph neural networks have attracted great attention and achieved prominent performance in various research fields. Most of those algorithms have assumed pairwise relationships of objects of interest. However, in many real applications, the relationships between objects are in higher-order, beyond a pairwise formulation. To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph attention. Whilst hypergraph convolution defines the basic formulation of performing convolution on a hypergraph, hypergraph attention further enhances the capacity of representation learning by leveraging an attention module. With the two operators, a graph neural network is readily extended to a more flexible model and applied to diverse applications where non-pairwise relationships are observed. Extensive experimental results with semi-supervised node classification demonstrate the effectiveness of hypergraph convolution and hypergraph attention.

arXiv commentAccepted by Pattern Recognition

References in corpus (12)

• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Graph Neural Networks: A Review of Methods and Applications
• Deep Convolutional Networks on Graph-Structured Data
• Representation Learning on Graphs with Jumping Knowledge Networks
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• Constrained Graph Variational Autoencoders for Molecule Design
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• Link Prediction Based on Graph Neural Networks
• NetGAN: Generating Graphs via Random Walks
• Deep Learning on Graphs: A Survey

Cited by in corpus (15)

• Session-based Recommendation with Hypergraph Attention Networks
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation
• Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs
• UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
• Hierarchical Hyperedge Embedding-based Representation Learning for Group Recommendation
• Temporal-Relational Hypergraph Tri-Attention Networks for Stock Trend Prediction
• Simplicial 2-Complex Convolutional Neural Nets
• Spectral Graph Attention Network with Fast Eigen-approximation
• HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
• Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models
• Directed hypergraph neural network
• Noise-robust classification with hypergraph neural network
• Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
• The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs
• Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks