MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks
This work addresses the problem of efficient adaptation of pre-trained GNNs for researchers and practitioners in graph learning, offering a parameter-efficient alternative to fine-tuning.
The paper tackles the challenge of adapting pre-trained graph neural networks to downstream tasks by proposing a message-adaptive graph prompt tuning method that injects learnable prompts into message passing, achieving consistent gains over prior methods in few-shot settings and competitive performance with fine-tuning in full-shot regimes.
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.