<ul><li>Graph learning models are effective in learning representations from graph data in various scenarios.</li><li>The 'pre-training, adaptation' scheme is commonly used for training graph learning models.</li><li>Graph prompting has emerged as a promising approach during the adaptation phase, allowing trainable prompts while keeping pre-trained models unchanged.</li><li>Recent advancements in graph prompting, pre-training methods, mainstream techniques, real-world applications, and future directions are reviewed in this paper.</li></ul>

Graph Prompting for Graph Learning Models: Recent Advances and Future Directions

Discover more