图转换器综述：架构、理论与应用
摘要
图转换器 (Graph Transformers) 通过解决图神经网络 (GNNs) 如过平滑和过压缩等固有局限性，展示了在建模图结构方面强大的能力。近期研究提出了多样化的架构、增强可解释性以及实际应用。鉴于这些快速发展，我们对图转换器进行了全面综述，涵盖架构、理论基础以及本综述中的应用等方面。我们根据处理结构信息的策略，将图转换器的架构分类，包括图分词、位置编码、结构感知注意力和模型集成。 Furthermore, from the theoretical perspective, we examine the expressivity of Graph Transformers in various discussed architectures and contrast them with other advanced graph learning algorithms to discover the connections. Furthermore, we provide a summary of the practical applications where Graph Transformers have been utilized, such as molecule, protein, language, vision, traffic, brain and material data. At the end of this survey, we will discuss the current challenges and prospective directions in Graph Transformers for potential future research.
引用
@article{arxiv.2502.16533,
title = {A Survey of Graph Transformers: Architectures, Theories and Applications},
author = {Chaohao Yuan and Kangfei Zhao and Ercan Engin Kuruoglu and Liang Wang and Tingyang Xu and Wenbing Huang and Deli Zhao and Hong Cheng and Yu Rong},
journal= {arXiv preprint arXiv:2502.16533},
year = {2025}
}