Hypergraph Neural Networks

TL;DR

This paper introduces Hypergraph Neural Networks (HGNN), a flexible framework for data representation learning that captures high-order data correlations using hypergraph structures and hyperedge convolution, outperforming existing methods.

Contribution

The paper proposes a novel HGNN framework that effectively encodes high-order data correlations through hyperedge convolution, enhancing data modeling for complex and multi-modal data.

Findings

HGNN outperforms state-of-the-art methods in citation network classification.

HGNN demonstrates superior performance on visual object recognition tasks.

The method is particularly effective for multi-modal data.

Abstract

In this paper, we present a hypergraph neural networks (HGNN) framework for data representation learning, which can encode high-order data correlation in a hypergraph structure. Confronting the challenges of learning representation for complex data in real practice, we propose to incorporate such data structure in a hypergraph, which is more flexible on data modeling, especially when dealing with complex data. In this method, a hyperedge convolution operation is designed to handle the data correlation during representation learning. In this way, traditional hypergraph learning procedure can be conducted using hyperedge convolution operations efficiently. HGNN is able to learn the hidden layer representation considering the high-order data structure, which is a general framework considering the complex data correlations. We have conducted experiments on citation network classification and visual object recognition tasks and compared HGNN with graph convolutional networks and other traditional methods. Experimental results demonstrate that the proposed HGNN method outperforms recent state-of-the-art methods. We can also reveal from the results that the proposed HGNN is superior when dealing with multi-modal data compared with existing methods.