Dynamic Heterogeneous Graph Representation Learning: A Survey

2026-09-04

AI Summary

本文针对动态异构图的表示学习问题，通过提出统一定义和新型分类法，系统性地回顾了相关方法，并指出了未来研究方向。

Abstract

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.

Problem

• Dynamic Heterogeneous Graphs
• Representation Learning
• Temporal Dynamics
• Structural Semantics

Innovation

• Dynamic Heterogeneous Graphs
• Temporal Granularity
• Algorithm-Centric Taxonomy
• Graph Neural Network (GNN)
• Transformer-based Methods