A systematic approach to random data augmentation on graph neural networks
This work addresses a practical problem for researchers and practitioners in graph machine learning by providing a systematic way to compare and improve random data augmentation methods, though it is incremental in building upon existing techniques.
The authors tackled the lack of standardization and comparability in random data augmentation (RDA) techniques for graph neural networks by proposing a comprehensive framework that unifies existing methods and enables systematic training and evaluation. Their approach led to new RDAs that improved state-of-the-art performance, as demonstrated in experiments.
Random data augmentations (RDAs) are state of the art regarding practical graph neural networks that are provably universal. There is great diversity regarding terminology, methodology, benchmarks, and evaluation metrics used among existing RDAs. Not only does this make it increasingly difficult for practitioners to decide which technique to apply to a given problem, but it also stands in the way of systematic improvements. We propose a new comprehensive framework that captures all previous RDA techniques. On the theoretical side, among other results, we formally prove that under natural conditions all instantiations of our framework are universal. On the practical side, we develop a method to systematically and automatically train RDAs. This in turn enables us to impartially and objectively compare all existing RDAs. New RDAs naturally emerge from our approach, and our experiments demonstrate that they improve the state of the art.