paper-with-me

Papers

A Cross-graph Tuning-free GNN Prompting Framework

2026-04-01 · Yaqi Chen, Shixun Huang, Ryan Twemlow, Lei Wang, John Le, Sheng Wang, Willy Susilo, Jun Yan, Jun Shen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.00399

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach

2025-01-25 · Qin Chen, Liang Wang, Bo Zheng, Guojie Song

The pre-train then fine-tune approach has advanced GNNs by enabling general knowledge capture without task-specific labels. However, an objective gap between pre-training and downstream tasks limits its effectiveness. Re…

General KnowledgeGraph Classification

Evaluating and Improving Graph to Text Generation with Large Language Models

2025-01-24 · Jie He, Yijun Yang, Wanqiu Long, Deyi Xiong 외

Large language models (LLMs) have demonstrated immense potential across various tasks. However, research for exploring and improving the capabilities of LLMs in interpreting graph structures remains limited. To address t…

DiversityFew-Shot LearningText Generation

StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs

2025-05-29 · Haohan Yuan, Sukhwa Hong, Haopeng Zhang

Large language models (LLMs) have shown strong performance in zero-shot summarization, but often struggle to model document structure and identify salient information in long texts. In this work, we introduce StrucSum, a…

Extractive SummarizationSentence

SGL-PT: A Strong Graph Learner with Graph Prompt Tuning

2023-02-24 · Yun Zhu, Jianhao Guo, Siliang Tang

Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inh…

Graph ClassificationGraph Learning

Robust Graph Fine-Tuning with Adversarial Graph Prompting

2026-01-01 · Ziyan Zhang, Bo Jiang, Jin Tang arxiv

Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to variou…

parameter-efficient fine-tuning