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

TL;DR

Hyper-SAGNN is a novel self-attention based graph neural network designed for hypergraphs, capable of handling various types and sizes, and demonstrating superior performance on multiple datasets and tasks including higher-order interaction prediction.

Contribution

The paper introduces Hyper-SAGNN, a versatile self-attention based GNN for hypergraphs that handles heterogeneous and variable-sized hyperedges, advancing beyond existing models.

Findings

Hyper-SAGNN outperforms state-of-the-art methods on benchmark datasets.

It achieves high accuracy in traditional graph tasks.

It effectively identifies outsiders in hypergraph data.

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.