Robustness meets accuracy in adversarial training for graph autoencoder

Abstract

Graph autoencoder (GAE) is an effective deep method for graph embedding, while it is vulnerable to the graph adversarial attacks. Adversarial training, which generates adversarial examples in the adversarial scope(neighborhood of natural examples), is effective to improve the robustness of GAE. However, it may lead to degradation of natural accuracy (accuracy on natural examples) due to the extra training examples generated in the adversarial scope (the reasonable scope of adversarial examples). Therefore, considering robustness and natural accuracy is crucial to GAE. In this paper, an improved GAE model is formulated by combining the Structure and Feature encoders, and a novel Adversarial Training strategy (GAE-SFAT) is proposed based on improved GAE. GAE-SFAT has a smaller but more reasonable adversarial scope for adversarial training, which keeps the robustness and reduces the degradation of natural accuracy compared with ordinary adversarial training. In addition, a novel algorithm considering the robustness and accuracy is designed to optimize the GAE-SFAT. We conduct experiments both on the natural graphs as well as perturbed graphs for three datasets. The results show that GAE-SFAT can perform better than state of arts adversarial training model under different kinds of perturbations.