Anomaly Node Detection Method Based on Variational Graph Auto-Encoders in Attribute Networks
LI Zhong1,2, JIN Xiaolong1,2, WANG Yajie1,2, MENG Lingbin1,2, ZHUANG Chuanzhi1,2, SUN Zhi1,2
1. Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190; 2. School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100049
Abstract：Graph neural network provides a method of combining structural information and attribute information for attribute network data mining. However, the current unsupervised attribute network anomaly node detection based on graph auto-encoder cannot capture the sub-features of normal nodes, and the false negative rate is high.Anomaly node detection method based on variational graph auto-encoders is proposed to detect abnormal nodes in attribute networks, containing two encoders and a decoder. A variational auto-encoder model consisting of an encoder and a decoder is designed to reconstruct the original input data. A decoder and the second encoder are utilized to learn the latent representation of the network without abnormal node data. The features of normal nodes are learned by the dual variational auto-encoder, and the reconstruction error is applied as the anomaly measure of nodes. Normal nodes composed of normal node features are identified as normal nodes by taking reconstruction error as the anomaly measurement of nodes. Experiments on real network datasets show that the proposed method is able to detect abnormal nodes in attribute networks effectively.
[1] AKOGLU L, TONG H H, KOUTRA D.Graph Based Anomaly Detection and Description: A Survey. Data Mining and Knowledge Discovery, 2015, 29(3): 626-688. [2] DING K Z, LI J D, LIU H.Interactive Anomaly Detection on Attributed Networks // Proc of the 20th ACM International Confe-rence on Web Search and Data Mining. New York, USA: ACM, 2019: 357-365. [3] CAO S S, LU W, XU Q K.Deep Neural Networks for Learning Graph Representations // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2016: 1145-1152. [4] GAO J, LIANG F, FAN W, et al. On Community Outliers and Their Efficient Detection in Information Networks // Proc of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2010: 813-822. [5] PEROZZI B, AKOGLU L, SÁNCHEZ P I, et al. Focused Clus-tering and Outlier Detection in Large Attributed Graphs // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2014: 1346-1355. [6] XU X W, YURUK N, FENG Z D, et al. SCAN: A Structural Clustering Algorithm for Networks // Proc of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2007: 824-833. [7] PEROZZI B, AKOGLU L.Scalable Anomaly Ranking of Attributed Neighborhoods // Proc of the 16th SIAM International Conference on Data Mining. Philadelphia, USA: SIAM, 2016: 207-215. [8] LUO M N, NIE F P, CHANG X J, et al. Adaptive Unsupervised Feature Selection with Structure Regularization. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(4): 944-956. [9] ZHAO X, WU Y H, LEE D L, et al. iForest: Interpreting Random Forests via Visual Analytics. IEEE Transactions on Visualization and Computer Graphics, 2019, 25(1): 407-416. [10] KIPF T N, WELLING M.Semi-supervised Classification with Graph Convolutional Networks[C/OL]. [2021-08-20].https://arxiv.org/pdf/1609.02907.pdf. [11] AKOGLU L, MCGLOHON M, FALOUTSOS C.Oddball: Spotting Anomalies in Weighted Graphs // Proc of the Pacific-Asia Confe-rence on Knowledge Discovery and Data Mining. Berlin, Germany: Springer, 2010: 410-421. [12] ROSSI R A, GALLAGHER B, NEVILLE J, et al. Modeling Dynamic Behavior in Large Evolving Graphs // Proc of the 6th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2013: 667-676. [13] TONG H H, LIN C Y.Non-negative Residual Matrix Factorization with Application to Graph Anomaly Detection // Proc of the 11th SIAM International Conference on Data Mining. Philadelphia, USA: SIAM, 2011: 143-153. [14] HENDERSON K, GALLAGHER B, ELIASSI-RAD T, et al. Rol-X: Structural Role Extraction & Mining in Large Graphs // Proc of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2012: 1231-1239. [15] PRAKASH B A, SRIDHARAN A, SESHADRI M, et al. Eigen-Spokes: Surprising Patterns and Scalable Community Chipping in Large Graphs // Proc of the Pacific-Asia Conference on Knowledge Discovery and Data Mining. Berlin, Germany: Springer, 2010: 435-448. [16] HOOI B, SONG H A, BEUTEL A, et al. FRAUDAR: Bounding Graph Fraud in the Face of Camouflage // Proc of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2016: 895-904. [17] SHIN K, HOOI B, FALOUTSOS C.M-Zoom: Fast Dense-Block Detection in Tensors with Quality Guarantees // Proc of the Joint European Conference on Machine Learning and Knowledge Disco-very in Databases. Berlin, Germany: Springer, 2016: 264-280. [18] SHIN K, HOOI B, KIM J, et al. D-Cube: Dense-Block Detection in Terabyte-Scale Tensors // Proc of the 10th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2017: 681-689. [19] HU R J, AGGARWAL C C, MA S, et al. An Embedding Approach to Anomaly Detection // Proc of the 32nd IEEE International Conference on Data Engineering. Washington, USA: IEEE, 2016: 385-396. [20] YU W C, CHENG W, AGGARWAL C C, et al. NetWalk: A Flexible Deep Embedding Approach for Anomaly Detection in Dynamic Networks // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 2672-2681. [21] 张君,张国英,刘玉树.基于属性相似度云模型的网络异常检测.吉林大学学报(工学版), 2006, 36(6): 954-957. (ZHANG J, ZHANG G Y, LIU Y S.Network Anomaly Detection Based on Attributes Similarity and Cloud Model. Journal of Jilin University(Engineering and Technology Edition), 2006, 36(6): 954-957.) [22] LI J D, DANI H, HU X, et al. RADAR: Residual Analysis for Anomaly Detection in Attributed Networks // Proc of the 26th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2017: 2152-2158. [23] PENG Z, LUO M N, LI J D, et al. ANOMALOUS: A Joint Mo-deling Approach for Anomaly Detection on Attributed Networks // Proc of the 27th International Joint Conference on Artificial Intelligence. New York, USA: ACM, 2018: 3513-3519. [24] DING K, LI J D, BHANUSHALI R, et al. Deep Anomaly Detection on Attributed Networks // Proc of the 19th SIAM International Conference on Data Mining. Philadelphia, USA: SIAM, 2019: 594-602. [25] PANG G S, SHEN C H D, JIN H, et al. Deep Weakly Supervised Anomaly Detection[C/OL].[2021-08-20]. https://arxiv.org/pdf/1910.13601.pdf. [26] LIU Y X, LI Z, PAN S R, et al. Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning. IEEE Transactions on Neural Networks and Learning Systems, 2021. DOI: 10.1109/TNNLS.2021.3068344. [27] AKCAY S, ATAPOUR-ABARGHOUEI A, BRECKON T P.GANomaly: Semi-supervised Anomaly Detection via Adversarial Trai-ning // Proc of the Asian Conference on Computer Vision. Berlin, Germany: Springer, 2018: 622-637. [28] 李忠,靳小龙,庄传志,等.面向图的异常检测研究综述.软件学报, 2021, 32(1): 167-193. (LI Z, JIN X L, ZHUANG C Z, et al. Overview on Graph Based Anomaly Detection. Journal of Software, 2021, 32(1): 167-193.) [29] LI Z, JIN X L, ZHUANG C Z, et al. Content-Aware Anomaly Detection with Network Representation Learning // Proc of the International Conference on Algorithms and Architectures for Parallel Processing. Berlin, Germany: Springer, 2020: 50-64. [30] BREUNIG M M, KRIEGEL H P, NG R T, et al. LOF: Identi-fying Density-Based Local Outliers. ACM SIGMOD Record, 2000, 29(2): 93-104. [31] VELIČKOVIĆP, FEDUS W, HAMILTON W L, et al. Deep Graph Infomax[C/OL]. [2021-08-20]. http://export.arxiv.org/pdf/1809.10341.
2022, Vol. 35 
