Appendix: CGLB: Benchmark Tasks for Continual Graph Learning

The other 30 classes of Aromaticity-CL are kept and constructed as 15 tasks. The name of the hyper-parameters are consistent with the names in our code. For the two multi-label classification datasets (SIDER-tIL and Tox21-tIL), early stopping is applied to ensure a stable performance. Table 1: Hyper-parameter candidates used for grid search. In this subsection, we explain the evaluation metrics in details.