Graph augmentation

Take a look to this two paper on graph augmentation (creating new examples from databases of graphs to improve training) https://arxiv.org/pdf/*******v4 code found in https://github.com/songtaoliu0823/lagnn and https://arxiv.org/pdf/*******v2 code found in https://github.com/fuvty/DeSCo I want you to read the papers and compare the approaches. In the report you need to give a brief description of the two approaches, the evaluation setup, the results and the conclusions you can test on the following grah classification datasets: MUTAG: https://paperswithcode.com/dataset/mutag PROTEINS: https://paperswithcode.com/dataset/proteins Predictive Toxicology Challenge (PTC): https://paperswithcode.com/dataset/ptc