Hyperbolic Heterogeneous Graph Attention Networks

arXiv:2404.09456v1 Announce Type: new
Abstract: 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 …

abstract arxiv attention cs.lg embedding embedding models graph graphs hierarchical however law low networks power power-law space them type vector