Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.08266 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918047259820032 |
|---|---|
| author | Wei, Yanbin Wang, Xuehao Zhuang, Zhan Chen, Yang Chen, Shuhao Zhang, Yulong Zhang, Yu Kwok, James |
| author_facet | Wei, Yanbin Wang, Xuehao Zhuang, Zhan Chen, Yang Chen, Shuhao Zhang, Yulong Zhang, Yu Kwok, James |
| contents | Message-passing graph neural networks (MPNNs) and structural features (SFs) are cornerstones for the link prediction task. However, as a common and intuitive mode of understanding, the potential of visual perception has been overlooked in the MPNN community. For the first time, we equip MPNNs with vision structural awareness by proposing an effective framework called Graph Vision Network (GVN), along with a more efficient variant (E-GVN). Extensive empirical results demonstrate that with the proposed frameworks, GVN consistently benefits from the vision enhancement across seven link prediction datasets, including challenging large-scale graphs. Such improvements are compatible with existing state-of-the-art (SOTA) methods and GVNs achieve new SOTA results, thereby underscoring a promising novel direction for link prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08266 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction Wei, Yanbin Wang, Xuehao Zhuang, Zhan Chen, Yang Chen, Shuhao Zhang, Yulong Zhang, Yu Kwok, James Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Message-passing graph neural networks (MPNNs) and structural features (SFs) are cornerstones for the link prediction task. However, as a common and intuitive mode of understanding, the potential of visual perception has been overlooked in the MPNN community. For the first time, we equip MPNNs with vision structural awareness by proposing an effective framework called Graph Vision Network (GVN), along with a more efficient variant (E-GVN). Extensive empirical results demonstrate that with the proposed frameworks, GVN consistently benefits from the vision enhancement across seven link prediction datasets, including challenging large-scale graphs. Such improvements are compatible with existing state-of-the-art (SOTA) methods and GVNs achieve new SOTA results, thereby underscoring a promising novel direction for link prediction. |
| title | Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.08266 |