When: Jul 7th, 2021 – 11:00 – 11:45 AM
Where: Google meet link
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 cannot predict variable-sized heterogeneous hyperedges. In this seminar, I will present a new self-attention based GNN called Hyper-SAGNN, which is applicable to homogeneous and heterogeneous hypergraphs with variable hyperedge sizes. Hyper-SAGNN significantly outperforms the state-of-the-art methods on traditional tasks, thus being useful for graph representation learning to uncover complex higher-order interactions in different applications.