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

2025-06-10

AI Summary

Graph prompting—adapting frozen pre-trained graph models to downstream tasks efficiently—lacks a unified theoretical framework and systematic methodology. Method: We propose the first unified taxonomy for graph prompting, decoupling graph structural priors from prompt design mechanisms. Our systematic approach integrates self-supervised pre-training, differentiable graph-structured prompting, task-aware subgraph masking, and domain-adaptive initialization. Contribution/Results: Evaluated across 30+ state-of-the-art methods and 10+ real-world applications—including drug discovery, social recommendation, and knowledge graph completion—our framework identifies and formalizes five fundamental open challenges. It establishes both theoretical foundations and practical paradigms for lightweight transfer learning in graph representation learning, enabling parameter-efficient adaptation without fine-tuning model weights.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

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.

Problem

• Review recent advances in graph prompting techniques
• Explore learnable prompt designs for graph models
• Address challenges in graph prompting for real-world applications

Innovation

• Self-supervised pre-training for graph models
• Learnable prompts for graph adaptation
• Systematic review of graph prompting techniques