ADMP-GNN: Adaptive Depth Message Passing GNN
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914015422185472 |
|---|---|
| author | Abbahaddou, Yassine Malliaros, Fragkiskos D. Lutzeyer, Johannes F. Vazirgiannis, Michalis |
| author_facet | Abbahaddou, Yassine Malliaros, Fragkiskos D. Lutzeyer, Johannes F. Vazirgiannis, Michalis |
| contents | Graph Neural Networks (GNNs) have proven to be highly effective in various graph learning tasks. A key characteristic of GNNs is their use of a fixed number of message-passing steps for all nodes in the graph, regardless of each node's diverse computational needs and characteristics. Through empirical real-world data analysis, we demonstrate that the optimal number of message-passing layers varies for nodes with different characteristics. This finding is further supported by experiments conducted on synthetic datasets. To address this, we propose Adaptive Depth Message Passing GNN (ADMP-GNN), a novel framework that dynamically adjusts the number of message passing layers for each node, resulting in improved performance. This approach applies to any model that follows the message passing scheme. We evaluate ADMP-GNN on the node classification task and observe performance improvements over baseline GNN models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_01170 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ADMP-GNN: Adaptive Depth Message Passing GNN Abbahaddou, Yassine Malliaros, Fragkiskos D. Lutzeyer, Johannes F. Vazirgiannis, Michalis Machine Learning Graph Neural Networks (GNNs) have proven to be highly effective in various graph learning tasks. A key characteristic of GNNs is their use of a fixed number of message-passing steps for all nodes in the graph, regardless of each node's diverse computational needs and characteristics. Through empirical real-world data analysis, we demonstrate that the optimal number of message-passing layers varies for nodes with different characteristics. This finding is further supported by experiments conducted on synthetic datasets. To address this, we propose Adaptive Depth Message Passing GNN (ADMP-GNN), a novel framework that dynamically adjusts the number of message passing layers for each node, resulting in improved performance. This approach applies to any model that follows the message passing scheme. We evaluate ADMP-GNN on the node classification task and observe performance improvements over baseline GNN models. |
| title | ADMP-GNN: Adaptive Depth Message Passing GNN |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.01170 |