Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
This addresses the need for generic models to handle higher-order interactions in various real-world applications, such as genomics, by providing a versatile solution for homogeneous and heterogeneous hypergraphs.
The paper tackled the problem of graph representation learning for hypergraphs, which lack models for variable-sized heterogeneous hyperedges, by developing Hyper-SAGNN, a self-attention based graph neural network that significantly outperforms state-of-the-art methods on benchmark datasets and achieves great performance on a new outsider identification task.
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.