让图神经网络更懂任务：动态调整邻居信息传递方式
MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks
- 在消息传递阶段插入可学习提示，动态重加权邻居信息
- 少样本场景下优于已有图提示方法，全量数据接近微调效果
- 适配多种图模型与预训练方式，零成本迁移实用性强
预训练图神经网络虽具备良好迁移能力，但将其适配下游任务仍具挑战，因预训练目标与任务需求不匹配。图提示调优提供了一种参数高效替代方案，但现有方法仅修改输入或表示，未改变消息传递过程，限制了对邻域交互的适应能力。本文提出消息自适应图提示调优（MAGPrompt），将可学习提示注入消息传递环节，在消息聚合时重新加权来自邻居的信息，并加入任务特定提示向量，同时保持骨干GNN冻结。该方法兼容主流GNN架构与预训练策略，适用于多种下游场景。在多样化的节点级与图级数据集上实验表明，少样本设置下持续优于先前图提示方法，全量样本设置下性能接近微调水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。