Data augmentation refers to a wide range of techniques for improving model generalization by augmenting training examples. Oftentimes such methods require domain knowledge about the dataset at hand, spawning a plethora of recent literature surrounding automated techniques for data augmentation. In this work we apply one such method, bilevel optimization, to tackle the problem of graph classification on the ogbg-molhiv dataset. Our best performing augmentation achieved a test ROCAUC score of 77.77 % with a GIN+virtual classifier, which makes it the most effective augmenter for this classifier on the leaderboard. This framework combines a GIN layer augmentation generator with a bias transformation and outperforms the same classifier augmented using the state-of-the-art FLAG augmentation.
@article{arxiv.2104.00722,
title = {GABO: Graph Augmentations with Bi-level Optimization},
author = {Heejung W. Chung and Avoy Datta and Chris Waites},
journal= {arXiv preprint arXiv:2104.00722},
year = {2021}
}