G-Mixup: Graph Data Augmentation for Graph Classification
This work addresses a domain-specific problem for graph machine learning by enabling effective data augmentation in non-Euclidean spaces, though it is incremental as it adapts an existing method to a new data type.
The paper tackles the challenge of applying mixup data augmentation to graph data for graph classification by proposing G-Mixup, which interpolates graphons of different classes to generate synthetic graphs, resulting in substantial improvements in generalization and robustness for graph neural networks as shown in extensive experiments.
This work develops \emph{mixup for graph data}. Mixup has shown superiority in improving the generalization and robustness of neural networks by interpolating features and labels between two random samples. Traditionally, Mixup can work on regular, grid-like, and Euclidean data such as image or tabular data. However, it is challenging to directly adopt Mixup to augment graph data because different graphs typically: 1) have different numbers of nodes; 2) are not readily aligned; and 3) have unique typologies in non-Euclidean space. To this end, we propose $\mathcal{G}$-Mixup to augment graphs for graph classification by interpolating the generator (i.e., graphon) of different classes of graphs. Specifically, we first use graphs within the same class to estimate a graphon. Then, instead of directly manipulating graphs, we interpolate graphons of different classes in the Euclidean space to get mixed graphons, where the synthetic graphs are generated through sampling based on the mixed graphons. Extensive experiments show that $\mathcal{G}$-Mixup substantially improves the generalization and robustness of GNNs.