发表机构
School of Cyberspace, Hangzhou Dianzi University; The University of Sydney; Zhejiang Provincial Key Laboratory for Sensitive Data Security Protection and Confidentiality Management（杭州电子科技大学网络空间学院; 悉尼大学; 浙江省敏感数据安全保护与保密管理重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述首次系统回顾动态异构图表示学习方法，提出涵盖离散与连续时间DHG的统一定义及以算法为中心的分类法，总结其应用、数据集与基准，并指出未来研究方向。
AI 中文摘要
图表示学习（Graph Representation Learning，GRL）是用于建模复杂网络的经典范式。然而，现实世界的AI系统本质上表现为具有复杂交互的演化异质实体，对静态或同质建模构成重大挑战。为应对这些复杂性，动态异构图（Dynamic Heterogeneous Graphs，DHG）的表示学习已成为学习低维表示的重要方法，该表示能同时保留结构语义和时间动态。本综述首次对DHG表示学习方法进行系统回顾。我们首先从时间粒度角度引入统一形式定义，涵盖离散时间和连续时间DHG。基于该公式，我们提出一种新颖的以算法为中心的分类法，对现有文献进行分类，包括早期基于嵌入的方法、基于图神经网络（Graph Neural Network，GNN）的模型以及较新的基于Transformer的DHG方法，同时明确强调它们在动态粒度方面的内在建模偏差。此外，我们总结了DHG表示学习的代表性应用，以及常用的数据集和基准。最后，我们讨论了有前景的研究方向，以指导这一快速发展领域的未来进展。
英文摘要
Graph representation learning (GRL) serves as a canonical paradigm for modeling complex networks. However, real-world AI systems inherently manifest as evolving heterogeneous entities with complex interactions, posing significant challenges to static or homogeneous modeling. To address these complexities, representation learning for Dynamic Heterogeneous Graphs (DHGs) has emerged as a vital approach for learning low-dimensional representations that simultaneously preserve structural semantics and temporal dynamics. This survey presents the first systematic review of DHG representation learning methods. We first introduce a unified formal definition that encompasses both discrete-time and continuous-time DHGs from the perspective of temporal granularity. Building upon this formulation, we propose a novel algorithm-centric taxonomy that categorizes existing literature, including early embedding-based approaches, graph neural network (GNN)-based models, and relatively recent Transformer-based DHG methods, while explicitly highlighting their intrinsic modeling biases with respect to dynamic granularity. Furthermore, we summarize representative applications of DHG representation learning, along with commonly used datasets and benchmarks. Finally, we discuss promising research directions that guide future advances in this rapidly evolving field.
CommentsIJCAI 2026 Survey Track
