图提示技术让预训练图模型更高效适配下游任务。
Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
- 用可学习的提示词替代修改模型，保持预训练结构不变。
- 在多个真实场景中提升图学习任务的性能表现。
- 适合想高效微调图模型的研究者和工程师参考。
图学习模型在各类现实场景中展现出从大规模图数据中学习表达性表示的强大能力。主流的“预训练-适配”策略先在无标签图数据上自监督预训练图模型，再将其适配到具体下游任务。适配阶段，图提示作为一种新兴方法，通过学习可训练的提示词来调整模型，同时保持预训练模型参数不变。本文系统综述了图提示的最新进展：首先介绍代表性图预训练方法，作为图提示的基础；其次回顾主流图提示技术，阐述其如何设计可学习提示；进一步总结图提示在不同领域的实际应用；最后讨论现有研究的开放挑战，并展望未来发展方向。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。