无需微调即可跨图通用的图神经网络提示框架
A Cross-graph Tuning-free GNN Prompting Framework
- 提出无需参数更新的跨图提示框架，直接部署于未知图
- 少样本任务上平均提升30.8%，最高达54%准确率
- 适合希望快速部署GNN模型的工程应用者
图神经网络提示旨在不需大量重训练的情况下适应不同任务和图结构。然而，现有大多数图提示方法仍需针对特定任务进行参数更新，并面临跨图泛化能力差的问题，限制了性能并削弱了提示技术的核心优势。本文提出一种跨图无微调提示框架（CTP），支持同质与异质图，可直接部署至未见图上而无需进一步参数调整，从而实现即插即用的GNN推理引擎。在少样本预测任务上的大量实验表明，相比当前最优方法，CTP平均准确率提升30.8%，最高提升54%，验证了其有效性，并为图提示学习提供了新视角。
原文摘要 · Abstract (English)
GNN prompting aims to adapt models across tasks and graphs without requiring extensive retraining. However, most existing graph prompt methods still require task-specific parameter updates and face the issue of generalizing across graphs, limiting their performance and undermining the core promise of prompting. In this work, we introduce a Cross-graph Tuning-free Prompting Framework (CTP), which supports both homogeneous and heterogeneous graphs, can be directly deployed to unseen graphs without further parameter tuning, and thus enables a plug-and-play GNN inference engine. Extensive experiments on few-shot prediction tasks show that, compared to SOTAs, CTP achieves an average accuracy gain of 30.8% and a maximum gain of 54%, confirming its effectiveness and offering a new perspective on graph prompt learning.
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。