A survey of dynamic graph neural networks

TL;DR

This survey reviews the development of dynamic graph neural networks, highlighting their techniques, models, challenges, and future research directions in capturing evolving graph data.

Contribution

It provides a comprehensive categorization and analysis of state-of-the-art dynamic GNN models, addressing their techniques, applications, and open challenges.

Findings

Dynamic GNNs outperform static models in evolving graph tasks.

Challenges include scalability and handling heterogeneous data.

Future directions involve adaptive, memory-enhanced, and inductive models.

Abstract

Graph neural networks (GNNs) have emerged as a powerful tool for effectively mining and learning from graph-structured data, with applications spanning numerous domains. However, most research focuses on static graphs, neglecting the dynamic nature of real-world networks where topologies and attributes evolve over time. By integrating sequence modeling modules into traditional GNN architectures, dynamic GNNs aim to bridge this gap, capturing the inherent temporal dependencies of dynamic graphs for a more authentic depiction of complex networks. This paper provides a comprehensive review of the fundamental concepts, key techniques, and state-of-the-art dynamic GNN models. We present the mainstream dynamic GNN models in detail and categorize models based on how temporal information is incorporated. We also discuss large-scale dynamic GNNs and pre-training techniques. Although dynamic GNNs have shown superior performance, challenges remain in scalability, handling heterogeneous information, and lack of diverse graph datasets. The paper also discusses possible future directions, such as adaptive and memory-enhanced models, inductive learning, and theoretical analysis.