Customizing Graph Neural Networks using Path Reweighting
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2021
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917779433586688 |
|---|---|
| author | Chen, Jianpeng Wang, Yujing Zeng, Ming Xiang, Zongyi Hou, Bitan Tong, Yunhai Mengshoel, Ole J. Ren, Yazhou |
| author_facet | Chen, Jianpeng Wang, Yujing Zeng, Ming Xiang, Zongyi Hou, Bitan Tong, Yunhai Mengshoel, Ole J. Ren, Yazhou |
| contents | Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph. Furthermore, we empirically analyze the semantics learned by CustomGNN and demonstrate its ability to avoid the three inherent problems in traditional GNNs, i.e., over-smoothing, poor robustness, and overfitting. In experiments with the node classification task, CustomGNN achieves state-of-the-art accuracies on three standard graph datasets and four large graph datasets. The source code of the proposed CustomGNN is available at \url{https://github.com/cjpcool/CustomGNN}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2106_10866 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Customizing Graph Neural Networks using Path Reweighting Chen, Jianpeng Wang, Yujing Zeng, Ming Xiang, Zongyi Hou, Bitan Tong, Yunhai Mengshoel, Ole J. Ren, Yazhou Machine Learning 68T07, 68T30, 68R99 I.2.0; I.2.4 Graph Neural Networks (GNNs) have been extensively used for mining graph-structured data with impressive performance. However, because these traditional GNNs do not distinguish among various downstream tasks, embeddings embedded by them are not always effective. Intuitively, paths in a graph imply different semantics for different downstream tasks. Inspired by this, we design a novel GNN solution, namely Customized Graph Neural Network with Path Reweighting (CustomGNN for short). Specifically, the proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph. Furthermore, we empirically analyze the semantics learned by CustomGNN and demonstrate its ability to avoid the three inherent problems in traditional GNNs, i.e., over-smoothing, poor robustness, and overfitting. In experiments with the node classification task, CustomGNN achieves state-of-the-art accuracies on three standard graph datasets and four large graph datasets. The source code of the proposed CustomGNN is available at \url{https://github.com/cjpcool/CustomGNN}. |
| title | Customizing Graph Neural Networks using Path Reweighting |
| topic | Machine Learning 68T07, 68T30, 68R99 I.2.0; I.2.4 |
| url | https://arxiv.org/abs/2106.10866 |