Reviews: N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

This is critical because most of the molecule datasets are small. Learning an unsupervised representation allows the model to better generalize and potentially utilize unlabeled data in a semi-supervised setting. Currently there are few methods working on learning unsupervised molecular representation and therefore I think this paper is original. The paper provides theoretical analysis characterizing the model's representation power and generalization bound, which is important for understanding the model. It would be good to see the average sparsity of c(n) on some molecule datasets.