H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912429687963648 |
|---|---|
| author | Nguyen, Trung-Kien Ping, Heng Li, Shixuan Zhang, Peiyu Kanakaris, Nikos Kotov, Nicholas Bogdan, Paul |
| author_facet | Nguyen, Trung-Kien Ping, Heng Li, Shixuan Zhang, Peiyu Kanakaris, Nikos Kotov, Nicholas Bogdan, Paul |
| contents | The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, known as the Graph Foundation Model (GFM). Existing research has leveraged text-attributed graphs (TAGs) to tackle the heterogeneity in node features among graphs. However, they primarily focus on homogeneous TAGs (HoTAGs), leaving heterogeneous TAGs (HeTAGs), where multiple types of nodes/edges reside, underexplored. To enhance the capabilities and applications of GFM, we introduce H$^2$GFM, a novel framework designed to generalize across both HoTAGs and HeTAGs. Our model projects diverse meta-relations among graphs under a unified textual space, and employs a context encoding to capture spatial and higher-order semantic relationships. To achieve robust node representations, we propose a novel context-adaptive graph transformer (CGT), effectively capturing information from both context neighbors and their relationships. Furthermore, we employ a mixture of CGT experts to capture the heterogeneity in structural patterns among graph types. Comprehensive experiments on a wide range of HoTAGs and HeTAGs as well as learning scenarios demonstrate the effectiveness of our model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs Nguyen, Trung-Kien Ping, Heng Li, Shixuan Zhang, Peiyu Kanakaris, Nikos Kotov, Nicholas Bogdan, Paul Machine Learning Social and Information Networks The growing interests and applications of graph learning in diverse domains have propelled the development of a unified model generalizing well across different graphs and tasks, known as the Graph Foundation Model (GFM). Existing research has leveraged text-attributed graphs (TAGs) to tackle the heterogeneity in node features among graphs. However, they primarily focus on homogeneous TAGs (HoTAGs), leaving heterogeneous TAGs (HeTAGs), where multiple types of nodes/edges reside, underexplored. To enhance the capabilities and applications of GFM, we introduce H$^2$GFM, a novel framework designed to generalize across both HoTAGs and HeTAGs. Our model projects diverse meta-relations among graphs under a unified textual space, and employs a context encoding to capture spatial and higher-order semantic relationships. To achieve robust node representations, we propose a novel context-adaptive graph transformer (CGT), effectively capturing information from both context neighbors and their relationships. Furthermore, we employ a mixture of CGT experts to capture the heterogeneity in structural patterns among graph types. Comprehensive experiments on a wide range of HoTAGs and HeTAGs as well as learning scenarios demonstrate the effectiveness of our model. |
| title | H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2506.08298 |