Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications
This work addresses a limitation in graph data augmentation for graph neural networks, offering a method that enhances performance in graph-level classification tasks, though it appears incremental by building on existing mixup and optimal transport techniques.
The paper tackles the problem of graph data augmentation for graph-level classifications by proposing FGWMixup, a novel mixup algorithm that jointly considers graph structures and signals using the Fused Gromov-Wasserstein metric, resulting in improved generalizability and robustness of GNNs across five datasets with both MPNNs and Graphormers backbones.
Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a midpoint of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from $\mathcal{O}(t^{-1})$ to $\mathcal{O}(t^{-2})$. Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs. Codes are available at https://github.com/ArthurLeoM/FGWMixup.