Spectral Adversarial Training for Robust Graph Neural Network
Authors:
- Jintang LiJLJintang Li
- Jiaying PengJPJiaying Peng
- Liang ChenLCLiang Chen
- Zibin ZhengZZZibin Zheng
- Tingting LiangTLTingting Liang
- Qing LingQLQing Ling
Preprint
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. \emph{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 Spectral Adversarial Training (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
This publication has 22 references indexed in Scilit:
- Batch virtual adversarial training for graph convolutional networksAI Open, 2023
- DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life ScienceACS Omega, 2021
- Adversarial Attack on Large Scale GraphIEEE Transactions on Knowledge and Data Engineering, 2021
- Robust graph convolutional networks with directional graph adversarial trainingApplied Intelligence, 2021
- Modelling High-Order Social Relations for Item RecommendationIEEE Transactions on Knowledge and Data Engineering, 2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Graph Adversarial Training: Dynamically Regularizing Based on Graph StructureIEEE Transactions on Knowledge and Data Engineering, 2019
- Eigenvector perturbations of complex networksPhysica A: Statistical Mechanics and its Applications, 2014
- Approximating spectral impact of structural perturbations in large networksPhysical Review E, 2010
- Automating the Construction of Internet Portals with Machine LearningInformation Retrieval Journal, 2000