S-Mixup: Structural Mixup for Graph Neural Networks

TL;DR

S-Mixup introduces a novel graph data augmentation technique that leverages structural information and gradient-based edge selection to improve node classification performance of GNNs, especially in heterophilous graphs.

Contribution

The paper proposes S-Mixup, a new mixup augmentation method for node classification that incorporates structural information and gradient-based edge selection, addressing limitations of previous graph mixup approaches.

Findings

S-Mixup improves GNN robustness and generalization.

It performs well on heterophilous graph datasets.

Experimental results show enhanced accuracy over baseline methods.

Abstract

Existing studies for applying the mixup technique on graphs mainly focus on graph classification tasks, while the research in node classification is still under-explored. In this paper, we propose a novel mixup augmentation for node classification called Structural Mixup (S-Mixup). The core idea is to take into account the structural information while mixing nodes. Specifically, S-Mixup obtains pseudo-labels for unlabeled nodes in a graph along with their prediction confidence via a Graph Neural Network (GNN) classifier. These serve as the criteria for the composition of the mixup pool for both inter and intra-class mixups. Furthermore, we utilize the edge gradient obtained from the GNN training and propose a gradient-based edge selection strategy for selecting edges to be attached to the nodes generated by the mixup. Through extensive experiments on real-world benchmark datasets, we demonstrate the effectiveness of S-Mixup evaluated on the node classification task. We observe that S-Mixup enhances the robustness and generalization performance of GNNs, especially in heterophilous situations. The source code of S-Mixup can be found at \url{https://github.com/SukwonYun/S-Mixup}