Hyperbolic Heterogeneous Graph Attention Networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911839435096064 |
|---|---|
| author | Park, Jongmin Han, Seunghoon Jeong, Soohwan Lim, Sungsu |
| author_facet | Park, Jongmin Han, Seunghoon Jeong, Soohwan Lim, Sungsu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_09456 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyperbolic Heterogeneous Graph Attention Networks Park, Jongmin Han, Seunghoon Jeong, Soohwan Lim, Sungsu Machine Learning 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. |
| title | Hyperbolic Heterogeneous Graph Attention Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.09456 |