A Comprehensive Survey on Deep Graph Representation Learning
Wei Ju, Zheng Fang, Yiyang Gu, Zequn Liu, Qingqing Long, Ziyue Qiao, Yifang Qin, Jianhao Shen, Fang Sun, Zhiping Xiao, Junwei Yang, Jingyang Yuan, Yusheng Zhao, Yifan Wang, Xiao Luo, Ming Zhang
TL;DR
This survey provides a comprehensive, taxonomy-driven panorama of deep graph representation learning, organizing methods by GNN architectures (graph convolutions, graph kernels, pooling, and transformers), learning paradigms (supervised, self-supervised, and structure learning), and key applications. It highlights how deep models leverage topology and attributes to improve node- and graph-level tasks across domains such as social analysis, molecular property prediction, recommender systems, and traffic analysis. The authors discuss core challenges (scalability, over-smoothing, 1-WL limitations, robustness, and interpretability) and offer future directions spanning application-driven and theory-driven avenues, including fairness, causality, and mathematical grounding. Overall, the work aims to unify rapidly evolving developments in deep graph representation learning and guide future research with a structured framework and forward-looking insights.
Abstract
Graph representation learning aims to effectively encode high-dimensional sparse graph-structured data into low-dimensional dense vectors, which is a fundamental task that has been widely studied in a range of fields, including machine learning and data mining. Classic graph embedding methods follow the basic idea that the embedding vectors of interconnected nodes in the graph can still maintain a relatively close distance, thereby preserving the structural information between the nodes in the graph. However, this is sub-optimal due to: (i) traditional methods have limited model capacity which limits the learning performance; (ii) existing techniques typically rely on unsupervised learning strategies and fail to couple with the latest learning paradigms; (iii) representation learning and downstream tasks are dependent on each other which should be jointly enhanced. With the remarkable success of deep learning, deep graph representation learning has shown great potential and advantages over shallow (traditional) methods, there exist a large number of deep graph representation learning techniques have been proposed in the past decade, especially graph neural networks. In this survey, we conduct a comprehensive survey on current deep graph representation learning algorithms by proposing a new taxonomy of existing state-of-the-art literature. Specifically, we systematically summarize the essential components of graph representation learning and categorize existing approaches by the ways of graph neural network architectures and the most recent advanced learning paradigms. Moreover, this survey also provides the practical and promising applications of deep graph representation learning. Last but not least, we state new perspectives and suggest challenging directions which deserve further investigations in the future.