mlsanityData to 7 Oct 2026

A Cross-graph Tuning-free GNN Prompting Framework

arXiv 2604.00399 ↗First posted 1 Apr 2026cs.LGcited by 0

Not on the map. Why?

Abstract (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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 44 references that are in the map. First posted on arXiv 1 Apr 2026.

Builds on

37 of 44 references.

References · 37

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  6. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  10. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  11. 2018Deep Graph Infomaxcited by 1,101
  12. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
25 more
  1. 2021An Explanation of In-context Learning as Implicit Bayesian Inferencecited by 915
  2. 2022Transformers learn in-context by gradient descentcited by 714
  3. 2022What learning algorithm is in-context learning? Investigations with linear modelscited by 671
  4. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  5. 2021MetaICL: Learning to Learn In Contextcited by 450
  6. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  7. 2019Composition-based Multi-Relational Graph Convolutional Networkscited by 395
  8. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  9. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  10. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  11. 2023All in One: Multi-task Prompting for Graph Neural Networkscited by 147
  12. 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
  13. 2023PRODIGY: Enabling In-context Learning Over Graphscited by 97
  14. 2020Graph Meta Learning via Local Subgraphscited by 89
  15. 2018One-Shot Relational Learning for Knowledge Graphscited by 78
  16. 2023Graph Prompt Learning: A Comprehensive Survey and Beyondcited by 61
  17. 2023HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learningcited by 45
  18. 2024Fully-inductive Node Classification on Arbitrary Graphscited by 36
  19. 2023AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNscited by 26
  20. 2022Self-Supervised Representation Learning via Latent Graph Predictioncited by 22
  21. 2025Edge Prompt Tuning for Graph Neural Networkscited by 18
  22. 2023GraphPro: Graph Pre-training and Prompt Learning for Recommendationcited by 17
  23. 2024Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractorscited by 13
  24. 2025GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learningcited by 6
  25. 2025Learning and Editing Universal Graph Prompt Tuning via Reinforcement Learningcited by 3

Built on by

Not cited yet.