Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to various graph datasets. In addition, the contrastive losses originally developed in computer vision have been directly applied to graph data, where the neighboring nodes are regarded as negatives and consequently pushed far apart from the anchor. However, this is contradictory with the homophily assumption of net-works that connected nodes often belong to theResearch goal: Does invariant rationale discovery in graph contrastive learning improve cross-domain generalization on node classification benchmarks compared to random augmentation strategies?Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.0/10.