Hypergraph convolution and hypergraph attention

Song Bai

doi:10.1016/j.patcog.2020.107637

Return

Hypergraph convolution and hypergraph attention

2021-02-01

333

Song Bai *

Feihu Zhang

Philip H. S. Torr

DOI：10.1016/j.patcog.2020.107637

Original

Save

View PDF

Abstract

En 中文

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 in-terest. 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. (c) 2020 Elsevier Ltd. All rights reserved.

Keywords:

Graph learning

Hypergraph learning

Graph neural networks

Semi-supervised learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.