A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges

TL;DR

This survey comprehensively reviews, compares, and evaluates 81 dynamic GNN models, 12 frameworks, and benchmarks, providing insights into their performance, challenges, and future research directions in dynamic graph neural networks.

Contribution

It offers the first thorough taxonomy, experimental comparison, and analysis of dynamic GNN models and frameworks, filling a significant gap in the literature.

Findings

Dynamic GNN models vary significantly in accuracy and efficiency.

Training frameworks impact convergence speed and resource usage.

Key challenges include scalability and real-time adaptability.

Abstract

Dynamic Graph Neural Networks (GNNs) combine temporal information with GNNs to capture structural, temporal, and contextual relationships in dynamic graphs simultaneously, leading to enhanced performance in various applications. As the demand for dynamic GNNs continues to grow, numerous models and frameworks have emerged to cater to different application needs. There is a pressing need for a comprehensive survey that evaluates the performance, strengths, and limitations of various approaches in this domain. This paper aims to fill this gap by offering a thorough comparative analysis and experimental evaluation of dynamic GNNs. It covers 81 dynamic GNN models with a novel taxonomy, 12 dynamic GNN training frameworks, and commonly used benchmarks. We also conduct experimental results from testing representative nine dynamic GNN models and three frameworks on six standard graph datasets. Evaluation metrics focus on convergence accuracy, training efficiency, and GPU memory usage, enabling a thorough comparison of performance across various models and frameworks. From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field.