In this paper, we conduct an empirical evaluation of Temporal Graph Benchmark (TGB) by extending our Dynamic Graph Library (DyGLib) to TGB. Compared with TGB, we include eleven popular dynamic graph learning methods for more exhaustive comparisons. Through the experiments, we find that (1) some issues need to be addressed in the current version of TGB, including mismatched data statistics, inaccurate evaluation metric computation, and so on; (2) different models depict varying performance across various datasets, which is in line with previous observations; (3) the performance of some baselines can be significantly improved over the reported results in TGB when using DyGLib. This work aims to ease the researchers' efforts in evaluating various dynamic graph learning methods on TGB and attempts to offer results that can be directly referenced in the follow-up research. All the used resources in this project are publicly available at https://github.com/yule-BUAA/DyGLib_TGB. This work is in progress, and feedback from the community is welcomed for improvements.

翻译：本文通过将我们的动态图库DyGLib扩展至时序图基准TGB，对其进行了实证评估。相较于TGB，我们纳入了十一种主流动态图学习方法以实现更全面的比较。通过实验发现：（1）当前版本TGB存在数据统计失配、评估指标计算不准确等问题亟待解决；（2）不同模型在不同数据集上表现各异，这与先前观察结果一致；（3）部分基线方法在使用DyGLib后的性能显著优于TGB中报告的结果。本研究旨在简化研究人员在TGB上评估各类动态图学习方法的复杂度，并尝试提供可直接用于后续研究的参考结果。本项目所有资源已公开于https://github.com/yule-BUAA/DyGLib_TGB。本工作仍在持续完善中，欢迎学界同仁反馈改进建议。