Hyper-SAGNN: a self-attention based graph neural network for hypergraphs

Abstract

Graph representation learning for hypergraphs can be used to extract patterns among higher-order interactions that are critically important in many real world problems. Current approaches designed for hypergraphs, however, are unable to handle different types of hypergraphs and are typically not generic for various learning tasks. Indeed, models that can predict variable-sized heterogeneous hyperedges have not been available. Here we develop a new self-attention based graph neural network called Hyper-SAGNN applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. We perform extensive evaluations on multiple datasets, including four benchmark network datasets and two single-cell Hi-C datasets in genomics. We demonstrate that Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks while also achieving great performance on a new task called outsider identification. Hyper-SAGNN will be useful for graph representation learning to uncover complex higher-order interactions in different applications.

References in corpus (5)

• Distributed Representations of Words and Phrases and their Compositionality
• Semi-Supervised Classification with Graph Convolutional Networks
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Inductive Representation Learning on Large Graphs
• Structural Deep Embedding for Hyper-Networks

Cited by in corpus (5)

• Interpreting Deep Learning-Based Networking Systems
• HNHN: Hypergraph Networks with Hyperedge Neurons
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• Neuralizing Efficient Higher-order Belief Propagation
• The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs