Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
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_ | 1866908447654543360 |
|---|---|
| author | Wei, Chu-Yuan Liu, Shun-Yao Zhuo, Sheng-Da Wang, Chang-Dong Huang, Shu-Qiang Guizani, Mohsen |
| author_facet | Wei, Chu-Yuan Liu, Shun-Yao Zhuo, Sheng-Da Wang, Chang-Dong Huang, Shu-Qiang Guizani, Mohsen |
| contents | Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based tasks (e.g., node classification or link prediction). Despite their triumphs, GNNs still face challenges such as long training and inference times, difficulty in capturing complex relationships, and insufficient feature extraction. To tackle these issues, graph pre-training and graph prompt methods have garnered increasing attention for their ability to leverage large-scale datasets for initial learning and task-specific adaptation, offering potential improvements in GNN performance. However, previous research has overlooked the potential of graph prompts in optimizing models, as well as the impact of both positive and negative graph prompts on model stability and efficiency. To bridge this gap, we propose a novel framework combining graph prompts with weight pruning, called GPAWP, which aims to enhance the performance and efficiency of graph prompts by using fewer of them. We evaluate the importance of graph prompts using an importance assessment function to determine positive and negative weights at different granularities. Through hierarchically structured pruning, we eliminate negative prompt labels, resulting in more parameter-efficient and competitively performing prompts. Extensive experiments on three benchmark datasets demonstrate the superiority of GPAWP, leading to a significant reduction in parameters in node classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09132 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning Wei, Chu-Yuan Liu, Shun-Yao Zhuo, Sheng-Da Wang, Chang-Dong Huang, Shu-Qiang Guizani, Mohsen Machine Learning Artificial Intelligence Graph Neural Networks (GNNs) have achieved remarkable success in various graph-based tasks (e.g., node classification or link prediction). Despite their triumphs, GNNs still face challenges such as long training and inference times, difficulty in capturing complex relationships, and insufficient feature extraction. To tackle these issues, graph pre-training and graph prompt methods have garnered increasing attention for their ability to leverage large-scale datasets for initial learning and task-specific adaptation, offering potential improvements in GNN performance. However, previous research has overlooked the potential of graph prompts in optimizing models, as well as the impact of both positive and negative graph prompts on model stability and efficiency. To bridge this gap, we propose a novel framework combining graph prompts with weight pruning, called GPAWP, which aims to enhance the performance and efficiency of graph prompts by using fewer of them. We evaluate the importance of graph prompts using an importance assessment function to determine positive and negative weights at different granularities. Through hierarchically structured pruning, we eliminate negative prompt labels, resulting in more parameter-efficient and competitively performing prompts. Extensive experiments on three benchmark datasets demonstrate the superiority of GPAWP, leading to a significant reduction in parameters in node classification tasks. |
| title | Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.09132 |