Automated Data Augmentations for Graph Classification
This work addresses the problem of improving graph classification performance for researchers and practitioners by automating data augmentations, though it is incremental as it builds on existing augmentation concepts.
The authors tackled the challenge of designing label-invariant data augmentations for graph classification, which is more difficult than for images, by proposing GraphAug, an automated method that uses reinforcement learning to maximize label-invariance probability, resulting in outperforming previous methods on various tasks.
Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related information of the graph, thereby producing label-invariant augmentations at most times. To ensure label-invariance, we develop a training method based on reinforcement learning to maximize an estimated label-invariance probability. Experiments show that GraphAug outperforms previous graph augmentation methods on various graph classification tasks.