Hyperbolic Heterogeneous Graph Attention Networks
This addresses the challenge of accurately modeling complex graph structures for applications in graph analysis, though it appears incremental as it builds on existing hyperbolic and attention-based methods.
The authors tackled the problem of representing complex heterogeneous graphs with hierarchical or power-law structures in Euclidean space, which causes distortions, by proposing Hyperbolic Heterogeneous Graph Attention Networks (HHGAT) that learn representations in hyperbolic spaces. The result shows that HHGAT outperforms state-of-the-art models in node classification and clustering tasks on three real-world datasets.
Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space. However, because heterogeneous graphs inherently possess complex structures, such as hierarchical or power-law structures, distortions can occur when representing them in Euclidean space. To overcome this limitation, we propose Hyperbolic Heterogeneous Graph Attention Networks (HHGAT) that learn vector representations in hyperbolic spaces with meta-path instances. We conducted experiments on three real-world heterogeneous graph datasets, demonstrating that HHGAT outperforms state-of-the-art heterogeneous graph embedding models in node classification and clustering tasks.