Moreover, the 47-th class of Products-CL contains only one node, and cannot be split for training,validation,andtest. We provide the set of splitting used in our experiments onourGitHub pageasareference. Thentheselected model is also automatically evaluated on the testing set. Details on the usage can be found in our GitHubpage. The name of the hyper-parameters are consistent with the names in our code.

Tothis end, we systematically study the task configurations in different application scenarios and develop a comprehensive Continual Graph Learning Benchmark (CGLB) curated from different public datasets.

Prediction APIs offered for afee area fast-growing industry and an important partofmachine learning asaservice.

To address these issues, we introduce a novel Bayesian meta-learning approach called meta-variational dropout (MetaVD).