Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.05567 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917251006857216 |
|---|---|
| author | Nguyen, Long D. Nguyen, Binh P. |
| author_facet | Nguyen, Long D. Nguyen, Binh P. |
| contents | Pre-trained graph neural networks (GNNs) transfer well, but adapting them to downstream tasks remains challenging due to mismatches between pre-training objectives and task requirements. Graph prompt tuning offers a parameter-efficient alternative to fine-tuning, yet most methods only modify inputs or representations and leave message passing unchanged, limiting their ability to adapt neighborhood interactions. We propose message-adaptive graph prompt tuning, which injects learnable prompts into the message passing step to reweight incoming neighbor messages and add task-specific prompt vectors during message aggregation, while keeping the backbone GNN frozen. The approach is compatible with common GNN backbones and pre-training strategies, and applicable across downstream settings. Experiments on diverse node- and graph-level datasets show consistent gains over prior graph prompting methods in few-shot settings, while achieving performance competitive with fine-tuning in full-shot regimes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_05567 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks Nguyen, Long D. Nguyen, Binh P. Machine Learning Pre-trained graph neural networks (GNNs) transfer well, but adapting them to downstream tasks remains challenging due to mismatches between pre-training objectives and task requirements. Graph prompt tuning offers a parameter-efficient alternative to fine-tuning, yet most methods only modify inputs or representations and leave message passing unchanged, limiting their ability to adapt neighborhood interactions. We propose message-adaptive graph prompt tuning, which injects learnable prompts into the message passing step to reweight incoming neighbor messages and add task-specific prompt vectors during message aggregation, while keeping the backbone GNN frozen. The approach is compatible with common GNN backbones and pre-training strategies, and applicable across downstream settings. Experiments on diverse node- and graph-level datasets show consistent gains over prior graph prompting methods in few-shot settings, while achieving performance competitive with fine-tuning in full-shot regimes. |
| title | MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.05567 |