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.
@article{arxiv.2604.00399,
title = {A Cross-graph Tuning-free GNN Prompting Framework},
author = {Yaqi Chen and Shixun Huang and Ryan Twemlow and Lei Wang and John Le and Sheng Wang and Willy Susilo and Jun Yan and Jun Shen},
journal= {arXiv preprint arXiv:2604.00399},
year = {2026}
}