Hypergraph Convolution and Hypergraph Attention

By Song Bai, Feihu Zhang, Philip H. S. Torr. Pattern Recognition, 2019

903 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Neurology

View Paper: https://www.semanticscholar.org/paper/6ed647b67c93901f302fa016a5355db8eebc7888

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongzhi Yin
2. Huan Liu
3. Jundong Li
4. Christopher Morris
5. Junliang Yu
6. Petra Mutzel
7. Gaurav Rattan
8. Pascal Poupart

In Neurology

1. Jie Yang
2. Jing Huang

Citations in the corpus

• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation (2021, background): “[2] introduce hypergraph attention to hypergraph convolutional networks to improve their capacity.”
• Next-item Recommendation with Sequential Hypergraphs (2020, background): “This naturally fits the assumption of the convolution operation [2, 3, 11, 19] that more propagation should be done between connected items.”
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View (2019, background): “HyperGraph (Bai, Zhang, and Torr 2019) Convolution&Attention FeaSt (Verma, Boyer, and Verbeek 2018) Convolution GraphSAGE (Hamilton, Ying, and Leskovec 2017) Convolution GAT (Veliˇckovi´c et al. 2018) Attention ARMA (Bianchi et al. 2019) Convolution GraphSAGE (Hamilton, Ying, and Leskovec 2017)…”
• Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings (2019, background): “Finally, there exists a new line of work focusing on extending GNNs to hypergraphs, see, e.g., (Bai et al., 2019; Yadati et al., 2019; Zhang et al., 2020), and a line of work in the data mining community incorporating global or higher-order information into graph or node embeddings, see, e.g., (Cao…”
• UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks (2021, methodology): “, 2019] and HyperConv [Bai et al., 2019] utilize the normalized hypergraph Laplacian, which essentially converts the hypergraphs to conventional graphs by viewing each hyperedge as a complete graph.”
• Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, background): “Some recent works study ways of handling such hyperedges for static (knowledge) graphs [233, 73, 239, 10].”