Identity-Preserving Adversarial Training for Robust Network Embedding  

作　　者：岑科廷 沈华伟 曹婍 徐冰冰 程学旗 Ke-Ting Cen;Hua-Wei Shen;Qi Cao;Bing-Bing Xu;Xue-Qi Cheng(Data Intelligence System Research Center,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 101480,China;Beijing Academy of Artificial Intelligence,Beijing 100000,China;Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology,Institute of Computing Technology Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]Data Intelligence System Research Center,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China [2]University of Chinese Academy of Sciences,Beijing 101480,China [3]Beijing Academy of Artificial Intelligence,Beijing 100000,China [4]Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology,Institute of Computing Technology Chinese Academy of Sciences,Beijing 100190,China

出　　处：《Journal of Computer Science & Technology》2024年第1期177-191,共15页计算机科学技术学报（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China under Grant Nos.U21B2046 and 62102402;the National Key Research and Development Program of China under Grant No.2020AAA0105200.

摘　　要：Network embedding,as an approach to learning low-dimensional representations of nodes,has been proved extremely useful in many applications,e.g.,node classification and link prediction.Unfortunately,existing network embed-ding models are vulnerable to random or adversarial perturbations,which may degrade the performance of network em-bedding when being applied to downstream tasks.To achieve robust network embedding,researchers introduce adversari-al training to regularize the embedding learning process by training on a mixture of adversarial examples and original ex-amples.However,existing methods generate adversarial examples heuristically,failing to guarantee the imperceptibility of generated adversarial examples,and thus limit the power of adversarial training.In this paper,we propose a novel method Identity-Preserving Adversarial Training(IPAT)for network embedding,which generates imperceptible adversarial exam-ples with explicit identity-preserving regularization.We formalize such identity-preserving regularization as a multi-class classification problem where each node represents a class,and we encourage each adversarial example to be discriminated as the class of its original node.Extensive experimental results on real-world datasets demonstrate that our proposed IPAT method significantly improves the robustness of network embedding models and the generalization of the learned node representations on various downstream tasks.

关 键 词：network embedding identity-preserving adversarial training adversarial the example 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]