Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Automated Data Augmentations for Graph Classification

Youzhi Luo · Michael McThrow · Wing Yee Au · Tao Komikado · Kanji Uchino · Koji Maruhashi · Shuiwang Ji

Keywords: [ data augmentation ] [ Label-invariance ] [ graph classification ] [ Deep Learning and representational learning ]


Abstract:

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.

Chat is not available.