Awesome-Graph-Prompting

A collection of Graph Prompting related works. A brief survey can be found in Zhihu: Graph Prompting.

Paper

All in One: Multi-Task Prompting for Graph Neural Networks. (KDD 2023 (Best Paper Award)) [paper] [code]
GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks. (KDD 2022) [Paper] [Code]
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks. (WWW 2023) [paper] [code]
PRODIGY: Enabling In-context Learning Over Graphs. (ICML 2023) [paper] [code]
SGL-PT: A Strong Graph Learner with Graph Prompt Tuning. (ArXiv) [paper]
Knowledge Graph Prompting for Multi-Document Question Answering. (ArXiv) [paper]
PROMPT TUNING FOR GRAPH NEURAL NETWORKS. (Withdrawn from ICML 2023) [paper] [openreview]
Natural Language is All a Graph Needs. (ArXiv) [paper]
Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer. (WWW 2023) [paper] [code]
Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction. (SIGIR 2023) [paper] [code]

StructGPT: A General Framework for Large Language Model to Reason over Structured Data. (ArXiv) [paper] [code]
Universal Prompt Tuning for Graph Neural Networks. (ArXiv) [paper]
CodeKGC: Code Language Model for Generative Knowledge Graph Construction. (ArXiv) [paper] [code]

A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges. (ArXiv) [paper]
Large Graph Models: A Perspective. (ArXiv) [paper]

[Prompt Engineering Guide.]
[awesome-large-graph-model]
[Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.]
[MaPLe: Multi-modal Prompt Learning.]
[The Power of Scale for Parameter-Efficient Prompt Tuning]