Hypergraph Neural Networks
This work addresses representation learning for complex, multi-modal data, offering a flexible framework that improves performance over existing graph-based methods.
The paper tackles the challenge of learning representations for complex data by proposing Hypergraph Neural Networks (HGNN), a framework that encodes high-order data correlations through hypergraph structures. Experimental results on citation network classification and visual object recognition tasks show that HGNN outperforms state-of-the-art methods, particularly for multi-modal data.
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.