[Appendix ] Graph Self-supervised Learning with Accurate Discrepancy Learning

Organization In Section A, we first introduce the baselines and our model and then describe the experimental details of graph classification and link prediction tasks but also our in-depth analyses. In this section, we first introduce the computing resources that we use, the baselines, and our model in Section A.1. After that, we describe the experimental setups of the graph classification and link prediction tasks in Section A.2 and Section A.3 as well as the analysis in Section A.4. Computing Resources For all experiments, we use PyTorch and PyTorch Geometric libraries [7, 1], for easy usage of GPU resources. We use TITAN XP and GeForce RTX 2080 Ti for training and evaluating all models. A.1 Baselines and Our Model 1. EdgePred is a predictive learning baseline adopted from the link prediction task of Hamilton et al. [2], whose goal is to predict the existence of edges between the given two nodes.