The proposed layers lead toamore data efficient representation and areduction in computation by exploiting symmetry. We evaluate chirality nets on the task ofhuman poseregression, which naturally exploits theleft/right mirroring ofthe human body.

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.

Typically, DNNs suffer from drastic performance degradation of previously learned tasksafterlearning newknowledge, which isawell-documented phenomenon, knownascatastrophic forgetting [8,9,10].

To Reviewer 1: [Intuition of benefits of advanced data augmentation] In line 198, we explained the theoretical3 connection between advanced data augmentation and better semi-supervised learning performance. We stated that4 "Importantly, the number of components is actually decided by the quality of the augmentation operation: an ideal5 augmentation should be able to reach all other examples of the same category given a starting instance.

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