An Empirical Evaluation of Temporal Graph Benchmark
This work provides a more exhaustive comparison for researchers in dynamic graph learning, though it is incremental as it builds on existing benchmarks and libraries.
The authors tackled the problem of evaluating dynamic graph learning methods by extending their Dynamic Graph Library (DyGLib) to the Temporal Graph Benchmark (TGB), finding that some baselines showed significantly improved performance over previously reported results.
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) different models depict varying performance across various datasets, which is in line with previous observations; (2) 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.