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

TL;DR

This paper reviews recent advances in graph prompting, a technique for adapting pre-trained graph models to downstream tasks by learning trainable prompts without altering the original models.

Contribution

It systematically summarizes recent methods, applications, and future challenges in graph prompting, highlighting its role in enhancing graph learning models.

Findings

Overview of key graph pre-training methods

Analysis of techniques for designing learnable prompts

Discussion of real-world applications and open challenges

Abstract

Graph learning models have demonstrated great prowess in learning expressive representations from large-scale graph data in a wide variety of real-world scenarios. As a prevalent strategy for training powerful graph learning models, the "pre-training, adaptation" scheme first pre-trains graph learning models on unlabeled graph data in a self-supervised manner and then adapts them to specific downstream tasks. During the adaptation phase, graph prompting emerges as a promising approach that learns trainable prompts while keeping the pre-trained graph learning models unchanged. In this paper, we present a systematic review of recent advancements in graph prompting. First, we introduce representative graph pre-training methods that serve as the foundation step of graph prompting. Next, we review mainstream techniques in graph prompting and elaborate on how they design learnable prompts for graph prompting. Furthermore, we summarize the real-world applications of graph prompting from different domains. Finally, we discuss several open challenges in existing studies with promising future directions in this field.