S-Mixup: Structural Mixup for Graph Neural Networks
Open Access
- 21 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4003-4007
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 https://github.com/SukwonYun/S-MixupKeywords
All Related Versions
Funding Information
- nstitute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (2022-0-00157)
- National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (2021R1C1C1009081)
This publication has 6 references indexed in Scilit:
- LTE4G2022
- Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure PreservationProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Mixup for Node and Graph Classification2021
- GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks2021
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- Lower bounds on the VC-dimension of smoothly parametrized function classes1994