Spectral Adversarial Training for Robust Graph Neural Network
- 15 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9240-9253
Abstract
Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations, known as adversarial examples . To address this issue, robust training methods against adversarial examples have received considerable attention in the literature. Adversarial Training (AT) is a successful approach to learning a robust model using adversarially perturbed training samples. Existing AT methods on GNNs typically construct adversarial perturbations in terms of graph structures or node features. However, they are less effective and fraught with challenges on graph data due to the discreteness of graph structure and the relationships between connected examples. In this work, we seek to address these challenges and propose S pectral A dversarial T raining (SAT), a simple yet effective adversarial training approach for GNNs. SAT first adopts a low-rank approximation of the graph structure based on spectral decomposition, and then constructs adversarial perturbations in the spectral domain rather than directly manipulating the original graph structure. To investigate its effectiveness, we employ SAT on three widely used GNNs. Experimental results on four public graph datasets demonstrate that SAT significantly improves the robustness of GNNs against adversarial attacks without sacrificing classification accuracy and training efficiency.Keywords
All Related Versions
Funding Information
- Key-Area Research and Development Program of Guangdong Province (2020B010165003)
- Basic and Applied Basic Research Foundation of Guangdong Province (2020A1515010831)
- Guangzhou Basic and Applied Basic Research Foundation (202102020881)
- CCF-AFSG Research Fund (20210002)
This publication has 28 references indexed in Scilit:
- Certifiable Robustness and Robust Training for Graph Convolutional Networks2019
- Robust Graph Convolutional Networks Against Adversarial Attacks2019
- Graph Neural Networks for Social Recommendation2019
- Adversarial Attacks on Neural Networks for Graph Data2018
- Adversarial Personalized Ranking for Recommendation2018
- Eigenvector perturbations of complex networksPhysica A: Statistical Mechanics and its Applications, 2014
- Approximating spectral impact of structural perturbations in large networksPhysical Review E, 2010
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Collective Classification in Network DataAI Magazine, 2008
- Automating the Construction of Internet Portals with Machine LearningInformation Retrieval Journal, 2000