Robust Regularization Design of Graph Neural Networks Against Adversarial Attacks Based on Lyapunov Theory  

作　　者：Wenjie YAN Ziqi LI Yongjun QI 

机构地区：[1]School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China [2]School of Computer Science and Engineering of North China Institute of Aerospace Engineering,Langfang 065000,China

出　　处：《Chinese Journal of Electronics》2024年第3期732-741,共10页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China (Grant No.61702157);the Doctoral Fund of North China Institute of Aerospace Engineering (Grant No.BKY-2022-09)。

摘　　要：The robustness of graph neural networks(GNNs)is a critical research topic in deep learning.Many researchers have designed regularization methods to enhance the robustness of neural networks,but there is a lack of theoretical analysis on the principle of robustness.In order to tackle the weakness of current robustness designing methods,this paper gives new insights into how to guarantee the robustness of GNNs.A novel regularization strategy named Lya-Reg is designed to guarantee the robustness of GNNs by Lyapunov theory.Our results give new insights into how regularization can mitigate the various adversarial effects on different graph signals.Extensive experiments on various public datasets demonstrate that the proposed regularization method is more robust than the state-of-theart methods such as L_(1)-norm,L_(2)-norm,L_(2)-norm,Pro-GNN,PA-GNN and GARNET against various types of graph adversarial attacks.

关 键 词：Deep learning Graph neural network ROBUSTNESS LYAPUNOV REGULARIZATION 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP309[自动化与计算机技术—控制科学与工程]