A General Benchmark Framework is Dynamic Graph Neural Network Need

TL;DR

Dynamic graph learning studies time-evolving graphs, contrasting with static graphs, and suffers from a lack of unified benchmarks. The paper argues for a benchmark framework that jointly captures temporal dynamics, evolving structures, and downstream tasks, and it surveys modeling approaches such as $TGNs$ and attention-based methods, downstream tasks, and domain applications. It emphasizes the need for standardized metrics, datasets, and experimental protocols to enable fair, meaningful comparisons and accelerate progress. By outlining the components of a comprehensive benchmark and highlighting current inconsistencies, the work aims to foster more robust evaluations and practical advances in dynamic graph learning.

Abstract

Dynamic graph learning is crucial for modeling real-world systems with evolving relationships and temporal dynamics. However, the lack of a unified benchmark framework in current research has led to inaccurate evaluations of dynamic graph models. This paper highlights the significance of dynamic graph learning and its applications in various domains. It emphasizes the need for a standardized benchmark framework that captures temporal dynamics, evolving graph structures, and downstream task requirements. Establishing a unified benchmark will help researchers understand the strengths and limitations of existing models, foster innovation, and advance dynamic graph learning. In conclusion, this paper identifies the lack of a standardized benchmark framework as a current limitation in dynamic graph learning research . Such a framework will facilitate accurate model evaluation, drive advancements in dynamic graph learning techniques, and enable the development of more effective models for real-world applications.