Unified robust network embedding framework for community detection via extreme adversarial attacks

被引:3
作者
Zhu, Wenjie [1 ,3 ]
Chen, Chunchun [1 ]
Peng, Bo [2 ]
机构
[1] China Jiliang Univ, Coll Informat Engn, Key Lab Electromagnet Wave Informat Technol & Metr, Hangzhou 310018, Zhejiang, Peoples R China
[2] Univ Queensland, Brisbane 4072, Australia
[3] China Jiliang Univ, Coll Informat Engn, Hangzhou 310018, Peoples R China
关键词
Robust community detection; Adversarial learning; Non-negative matrix factorization; Network embedding; GRAPH; NODE;
D O I
10.1016/j.ins.2023.119200
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Graph data are widely available in complex network systems. Numerous community detection algorithms have been investigated to study graph problems wherein the network topology offers abundant behavioral and functional information. In real scenarios, networks are extremely susceptible to external perturbations, primarily because of sparse topological information. Consequently, maintaining robust community detection performance when confronted with intricate network attacks or perturbations is challenging. Previous anti-graph perturbation methods have typically been adjusted to specific perturbation types, leading to the degradation or failure of these defences when confronted with other types of attack. Accordingly, a unified robust framework that leverages extreme adversarial attacks is proposed in this paper. Specifically, a novel graph perturbation module is introduced into the model to generate extreme undirected or directed perturbations through dynamic updating; this ensures that the model can fit the attacked network well. The proposed framework derives a unified perturbation formulation capable of simultaneously attacking symmetric and asymmetric networks. Furthermore, this framework can be applied to many existing non-negative matrix factorization-based community detection methods. Extensive experiments on artificial and real-world networks demonstrate that the proposed framework significantly improves the robustness of detection tasks, particularly in noisy networks.
引用
收藏
页数:16
相关论文
共 50 条
[21]   Robust Object Detection via Adversarial Novel Style Exploration [J].
Wang, Wen ;
Zhang, Jing ;
Zhai, Wei ;
Cao, Yang ;
Tao, Dacheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 :1949-1962
[22]   Adversarial concept drift detection under poisoning attacks for robust data stream mining [J].
Korycki, Lukasz ;
Krawczyk, Bartosz .
MACHINE LEARNING, 2023, 112 (10) :4013-4048
[23]   Adversarial concept drift detection under poisoning attacks for robust data stream mining [J].
Łukasz Korycki ;
Bartosz Krawczyk .
Machine Learning, 2023, 112 :4013-4048
[24]   Network Embedding-based Directed Community Detection with Unknown Community Number [J].
Zhang, Qingzhao ;
Zhou, Jinlong ;
Ren, Mingyang .
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2024,
[25]   Dual Supervised Network Embedding Based Community Detection Algorithm [J].
Zheng W. ;
Wang Y. ;
Yang G. .
Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence, 2022, 35 (03) :283-290
[26]   A Network Embedding-Enhanced Approach for Generalized Community Detection [J].
He, Dongxiao ;
Yang, Xue ;
Feng, Zhiyong ;
Chen, Shizhan ;
Fogelman-Soulie, Francoise .
KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2018, PT II, 2018, 11062 :383-395
[27]   A Framework for Accurate Community Detection on Signed Networks Using Adversarial Learning [J].
Kang, David Y. ;
Lee, Woncheol ;
Lee, Yeon-Chang ;
Han, Kyungsik ;
Kim, Sang-Wook .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (11) :10937-10951
[28]   Robust Android Malware Detection System Against Adversarial Attacks Using Q-Learning [J].
Rathore, Hemant ;
Sahay, Sanjay K. ;
Nikam, Piyush ;
Sewak, Mohit .
INFORMATION SYSTEMS FRONTIERS, 2021, 23 (04) :867-882
[29]   Robust Android Malware Detection System Against Adversarial Attacks Using Q-Learning [J].
Hemant Rathore ;
Sanjay K. Sahay ;
Piyush Nikam ;
Mohit Sewak .
Information Systems Frontiers, 2021, 23 :867-882
[30]   Correction: Adversarial concept drift detection under poisoning attacks for robust data stream mining [J].
Łukasz Korycki ;
Bartosz Krawczyk .
Machine Learning, 2024, 113 :3303-3304