Mixup in Latent Geometry for Graph Classification
Open Access
- 21 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 11 (6) , 5943-5953
Abstract
Mixup is a data augmentation method which can interpolate between existing data to create new samples. By enlarging the training distribution, it reduces the risk of overfitting and improves generalization. Mixup is relatively straightforward to apply to image samples because pixels with equivalent coordinates in different images can be associated. However, alignment of distinct graphs with different sizes is non-trivial, thereby hindering the application of Mixup to graph data. Here we develop a novel algorithm to address this issue by exploiting the latent hyperbolic geometry which has been shown to underlie many real-world graphs. By considering global graph structure similarity and several fundamental structural features of graph models, we demonstrate that our mixup scheme leads to synthetic graphs whose structural features approximate the linear interpolation of parent graphs, a property important for avoiding the generation of mislabeled synthetic data. We apply the proposed algorithm to classify empirical graphs, and the results show that it improves classification performance on all six benchmark datasets and significantly enhances the generalization ability and robustness of graph neural networks.Keywords
Funding Information
- National Natural Science Foundation of China (12161141016, T2225022, 12150410309)
- Shuguang Program of Shanghai Education Development Foundation
- Shanghai Municipal Education Commission (22SG21)
- Shanghai Municipal Science and Technology (2021SHZDZX0100)
- Shanghai Municipal Commission of Science and technology (19511132101)
- Fundamental Research Funds for the Central Universities
This publication has 39 references indexed in Scilit:
- Graph Neural Networks2022
- Implications of the school-household network structure on SARS-CoV-2 transmission under school reopening strategies in EnglandNature Communications, 2021
- Community detection in social recommender systems: a surveyApplied Intelligence, 2020
- System-level matching of structural and functional connectomes in the human brainNeuroImage, 2019
- Quantification of network structural dissimilaritiesNature Communications, 2017
- Popularity versus similarity in growing networksNature, 2012
- The graph matching problemPattern Analysis and Applications, 2012
- Error and attack tolerance of complex networksNature, 2000
- Stochastic blockmodels: First stepsSocial Networks, 1983
- An algorithm to solve the m × n assignment problem in expected time O(mn log n)Networks, 1980