Graph contrastivelearning (GCL), by training GNNs to maximize the correspondence between the representations of the same graph in its different augmented forms, may yield robust and transferable GNNs even without using labels.

Graph Contrastive Learning (GCL), learning the node representations by augmenting graphs, has attracted considerable attentions.

Such asymmetry presents two issues.

Data augmentation plays a key role in modern machine learning pipelines.

Augmentation strategies The augmentation idea of ANODEs (Dupont et al., 2019) is taken further and generalized to novel dynamical system-inspired and parameter efficient alternatives, relyingondifferentchoicesofhx in(1).