ifMixup: Interpolating Graph Pair to Regularize Graph Classification
This addresses the challenge of applying Mixup-like regularization to graphs with arbitrary structures, which is a domain-specific problem for graph learning.
The paper tackled the problem of improving generalization in Graph Neural Networks (GNNs) for graph classification by proposing ifMixup, an interpolation-based regularization technique that aligns and mixes graph pairs, resulting in superior predictive accuracy compared to existing methods.
We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classification. We leverage Mixup, an effective regularizer for vision, where random sample pairs and their labels are interpolated to create synthetic images for training. Unlike images with grid-like coordinates, graphs have arbitrary structure and topology, which can be very sensitive to any modification that alters the graph's semantic meanings. This posts two unanswered questions for Mixup-like regularization schemes: Can we directly mix up a pair of graph inputs? If so, how well does such mixing strategy regularize the learning of GNNs? To answer these two questions, we propose ifMixup, which first adds dummy nodes to make two graphs have the same input size and then simultaneously performs linear interpolation between the aligned node feature vectors and the aligned edge representations of the two graphs. We empirically show that such simple mixing schema can effectively regularize the classification learning, resulting in superior predictive accuracy to popular graph augmentation and GNN methods.