Hypergraph Convolution and Hypergraph Attention

TL;DR

This paper introduces hypergraph convolution and hypergraph attention operators to extend graph neural networks for modeling high-order relationships, demonstrating improved performance in semi-supervised node classification tasks.

Contribution

The paper presents novel hypergraph convolution and attention mechanisms, enabling neural networks to effectively learn from high-order, non-pairwise relationships in graph-structured data.

Findings

Hypergraph operators improve node classification accuracy.

Enhanced representation learning with hypergraph attention.

Effective extension of GNNs to high-order data.

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.