Saved in:
Bibliographic Details
Main Authors: Chen, Yaqi, Huang, Shixun, Twemlow, Ryan, Wang, Lei, Le, John, Wang, Sheng, Susilo, Willy, Yan, Jun, Shen, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.00399
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.