Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916919670472704 |
|---|---|
| author | Kim, Jongwoo Chu, Seongyeub Park, Hyeongmin Wong, Bryan Han, Keejun Yi, Mun Yong |
| author_facet | Kim, Jongwoo Chu, Seongyeub Park, Hyeongmin Wong, Bryan Han, Keejun Yi, Mun Yong |
| contents | Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths, which are coarse-grained and focus solely on aspects like node type, limiting their ability to capture complex interactions. We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. MF2Vec extracts paths via random walks and generates multi-faceted vectors, ignoring predefined schemas. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering. Extensive experiments show that MF2Vec outperforms existing methods, offering a more flexible and comprehensive framework for analyzing complex networks. The code is available at https://anonymous.4open.science/r/MF2Vec-6ABC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning Kim, Jongwoo Chu, Seongyeub Park, Hyeongmin Wong, Bryan Han, Keejun Yi, Mun Yong Machine Learning Artificial Intelligence Recent advancements in graph neural networks (GNNs) and heterogeneous GNNs (HGNNs) have advanced node embeddings and relationship learning for various tasks. However, existing methods often rely on domain-specific predefined meta-paths, which are coarse-grained and focus solely on aspects like node type, limiting their ability to capture complex interactions. We introduce MF2Vec, a model that uses multi-faceted (fine-grained) paths instead of predefined meta-paths. MF2Vec extracts paths via random walks and generates multi-faceted vectors, ignoring predefined schemas. This method learns diverse aspects of nodes and their relationships, constructs a homogeneous network, and creates node embeddings for classification, link prediction, and clustering. Extensive experiments show that MF2Vec outperforms existing methods, offering a more flexible and comprehensive framework for analyzing complex networks. The code is available at https://anonymous.4open.science/r/MF2Vec-6ABC. |
| title | Leveraging Multi-facet Paths for Heterogeneous Graph Representation Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.20648 |