Characterizing the Influence of Topology on Graph Learning Tasks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911835902443520 |
|---|---|
| author | Wu, Kailong Xie, Yule Ding, Jiaxin Ren, Yuxiang Fu, Luoyi Wang, Xinbing Zhou, Chenghu |
| author_facet | Wu, Kailong Xie, Yule Ding, Jiaxin Ren, Yuxiang Fu, Luoyi Wang, Xinbing Zhou, Chenghu |
| contents | Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph topology influences the performance of learning models on downstream tasks has not yet been well understood. In this paper, we propose a metric, TopoInf, which characterizes the influence of graph topology by measuring the level of compatibility between the topological information of graph data and downstream task objectives. We provide analysis based on the decoupled GNNs on the contextual stochastic block model to demonstrate the effectiveness of the metric. Through extensive experiments, we demonstrate that TopoInf is an effective metric for measuring topological influence on corresponding tasks and can be further leveraged to enhance graph learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07493 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Characterizing the Influence of Topology on Graph Learning Tasks Wu, Kailong Xie, Yule Ding, Jiaxin Ren, Yuxiang Fu, Luoyi Wang, Xinbing Zhou, Chenghu Machine Learning Artificial Intelligence Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph topology influences the performance of learning models on downstream tasks has not yet been well understood. In this paper, we propose a metric, TopoInf, which characterizes the influence of graph topology by measuring the level of compatibility between the topological information of graph data and downstream task objectives. We provide analysis based on the decoupled GNNs on the contextual stochastic block model to demonstrate the effectiveness of the metric. Through extensive experiments, we demonstrate that TopoInf is an effective metric for measuring topological influence on corresponding tasks and can be further leveraged to enhance graph learning. |
| title | Characterizing the Influence of Topology on Graph Learning Tasks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.07493 |