ABSTRACT
Anomaly detection on graphs has recently attracted considerable attention due to its broad range of high-impact applications, including cybersecurity, financial transactions, and recommendation systems. Although many efforts have thus far been made, how to effectively handle the high inconsistency between users' behavior and labels, a fundamental issue in anomaly detection, has not yet received sufficient concern. Moreover, the inconsistency problem is hard to investigate and even deteriorates the performance of anomaly detectors. To this end, we propose a novel graph self-supervised learning framework, Capsule Graph Infomax (termed CapsGI), to overcome the inconsistency of anomaly detection. Inspired by the recent advances of capsules on images, we explore another possibility of reforming the node embedding by capsule ideas to represent the unique node's properties. Concretely, by disentangling heterogeneous factors underlying each node representation, we can establish node capsules such that their representation can reflect intrinsic node properties. To strengthen the connection among normal nodes, CapsGI further represents the part-whole contrastive learning between lower-level capsules (part) and higher-level capsules (whole) by explicitly considering the context graph relations. Extensive experiments on multiple real-world datasets demonstrate that our model significantly outperforms state-of-the-art models.
Supplemental Material
- Parnian Afshar, Arash Mohammadi, and Konstantinos N. Plataniotis. 2018. Brain Tumor Type Classification via Capsule Networks. In ICIP. IEEE, 3129--3133. https: //doi.org/10.1109/ICIP.2018.8451379Google ScholarCross Ref
- Leman Akoglu, Rishi Chandy, and Christos Faloutsos. 2013. Opinion Fraud Detection in Online Reviews by Network Effects. In ICWSM. The AAAI Press.Google Scholar
- Adam Breuer, Roee Eilat, and Udi Weinsberg. 2020. Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks. In WWW. ACM / IW3C2, 1287--1297.Google Scholar
- Corinna Cortes, Daryl Pregibon, and Chris Volinsky. 2001. Communities of Interest. In IDA, Vol. 2189. Springer, 105--114.Google Scholar
- Qi Ding, Natallia Katenka, Paul Barford, Eric D. Kolaczyk, and Mark Crovella. 2012. Intrusion as (anti)social communication: characterization and detection. In SIGKDD. ACM, 886--894.Google Scholar
- Yingtong Dou,Weijian Li, Zhirong Liu, Zhenhua Dong, Jiebo Luo, and Philip S. Yu. 2019. Uncovering download fraud activities in mobile app markets. In ASONAM. 671--678.Google Scholar
- Yingtong Dou, Zhiwei Liu, Li Sun, Yutong Deng, Hao Peng, and Philip S. Yu. 2020. Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters. In CIKM. ACM, 315--324.Google Scholar
- Kevin Duarte, Yogesh S. Rawat, and Mubarak Shah. 2018. VideoCapsuleNet: A Simplified Network for Action Detection. In NeurIPS. 7621--7630.Google Scholar
- Gongfan Fang, Jie Song, XinchaoWang, Chengchao Shen, XingenWang, and Mingli Song. 2021. ContrastiveModel Inversion for Data-Free Knowledge Distillation. CoRR abs/2105.08584 (2021).Google Scholar
- William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NIPS. 1024--1034.Google Scholar
- Peng He, Yue Zhou, Shukai Duan, and Xiaofang Hu. 2022. Memristive Residual CapsNet: A hardware friendly multi-level capsule network. Neurocomputing 496 (2022), 1--10.Google ScholarDigital Library
- Geoffrey E. Hinton, Sara Sabour, and Nicholas Frosst. 2018. Matrix capsules with EM routing. In ICLR. OpenReview.net.Google Scholar
- Bryan Hooi, Hyun Ah Song, Alex Beutel, Neil Shah, Kijung Shin, and Christos Faloutsos. 2016. FRAUDAR: Bounding Graph Fraud in the Face of Camouflage. In SIGKDD. ACM, 895--904.Google Scholar
- Yifan Hou, Jian Zhang, James Cheng, Kaili Ma, Richard T. B. Ma, Hongzhi Chen, and Ming-Chang Yang. 2022. Measuring and Improving the Use of Graph Information in Graph Neural Networks. CoRR abs/2206.13170 (2022).Google Scholar
- Ayush Jaiswal, Wael AbdAlmageed, Yue Wu, and Premkumar Natarajan. 2018. CapsuleGAN: Generative Adversarial Capsule Network. In ECCV (Lecture Notes in Computer Science), Vol. 11131. Springer, 526--535.Google Scholar
- George Karypis and Vipin Kumar. 1995. Multilevel Graph Partitioning Schemes. In ICMR. CRC Press, 113--122.Google Scholar
- Thomas N. Kipf and Max Welling. 2016. Variational Graph Auto-Encoders. CoRR abs/1611.07308 (2016).Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR. OpenReview.net.Google Scholar
- Srijan Kumar, Bryan Hooi, Disha Makhija, Mohit Kumar, Christos Faloutsos, and V. S. Subrahmanian. 2018. REV2: Fraudulent User Prediction in Rating Platforms. In WSDM. ACM, 333--341.Google Scholar
- Srijan Kumar, Francesca Spezzano, V. S. Subrahmanian, and Christos Faloutsos. 2016. Edge Weight Prediction in Weighted Signed Networks. In ICDM. IEEE Computer Society, 221--230.Google Scholar
- Srijan Kumar, Xikun Zhang, and Jure Leskovec. 2019. Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks. In KDD. ACM, 1269--1278.Google Scholar
- Namkyeong Lee, Junseok Lee, and Chanyoung Park. 2022. Augmentation-Free Self-Supervised Learning on Graphs. In AAAI. AAAI Press, 7372--7380.Google Scholar
- Xiangfeng Li, Shenghua Liu, Zifeng Li, Xiaotian Han, Chuan Shi, Bryan Hooi, He Huang, and Xueqi Cheng. 2020. FlowScope: Spotting Money Laundering Based on Graphs. In AAAI. AAAI Press, 4731--4738.Google Scholar
- Huawen Liu, Enhui Li, Xinwang Liu, Kaile Su, and Shichao Zhang. 2021. Anomaly Detection With Kernel Preserving Embedding. ACM Trans. Knowl. Discov. Data 15, 5 (2021), 91:1--91:18.Google ScholarDigital Library
- Yixin Liu, Zhao Li, Shirui Pan, Chen Gong, Chuan Zhou, and George Karypis. 2022. Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning. IEEE Trans. Neural Networks Learn. Syst. 33, 6 (2022), 2378--2392.Google ScholarCross Ref
- Ziqi Liu, Chaochao Chen, Longfei Li, Jun Zhou, Xiaolong Li, Le Song, and Yuan Qi. 2019. GeniePath: Graph Neural Networks with Adaptive Receptive Paths. In AAAI. AAAI Press, 4424--4431. https://doi.org/10.1609/aaai.v33i01.33014424Google ScholarDigital Library
- Zhiwei Liu, Yingtong Dou, Philip S. Yu, Yutong Deng, and Hao Peng. 2020. Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection. In SIGIR. ACM, 1569--1572.Google Scholar
- Jianxin Ma, Peng Cui, Kun Kuang, Xin Wang, and Wenwu Zhu. 2019. Disentangled Graph Convolutional Networks. In ICML (Proceedings of Machine Learning Research), Vol. 97. PMLR, 4212--4221.Google Scholar
- Julian J. McAuley and Jure Leskovec. 2013. From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. In WWW. ACM, 897--908.Google Scholar
- Hamed Nilforoshan and Neil Shah. 2019. SliceNDice: Mining Suspicious Multi- Attribute Entity Groups with Multi-View Graphs. In DSAA. IEEE, 351--363.Google Scholar
- Shebuti Rayana and Leman Akoglu. 2015. Collective Opinion Spam Detection: Bridging Review Networks and Metadata. In SIGKDD. ACM, 985--994.Google Scholar
- Sara Sabour, Nicholas Frosst, and Geoffrey E. Hinton. 2017. Dynamic Routing Between Capsules. In USA. 3856--3866.Google ScholarDigital Library
- Neil Shah, Alex Beutel, Brian Gallagher, and Christos Faloutsos. 2014. Spotting Suspicious Link Behavior with fBox: An Adversarial Perspective. In ICDM. IEEE Computer Society, 959--964.Google Scholar
- Kijung Shin, Bryan Hooi, and Christos Faloutsos. 2016. M-Zoom: Fast Dense- Block Detection in Tensors with Quality Guarantees. In ECML PKDD (Lecture Notes in Computer Science), Vol. 9851. Springer, 264--280.Google Scholar
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2017. Graph Attention Networks. CoRR abs/1710.10903 (2017). http://arxiv.org/abs/1710.10903Google Scholar
- Petar Velickovic, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, and R. Devon Hjelm. 2019. Deep Graph Infomax. In ICLR. OpenReview.net.Google Scholar
- Daixin Wang, Yuan Qi, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, and Shuang Yang. 2019. A Semi-Supervised Graph Attentive Network for Financial Fraud Detection. In ICDM. IEEE, 598--607.Google Scholar
- Guan Wang, Sihong Xie, Bing Liu, and Philip S. Yu. 2011. Review Graph Based Online Store Review Spammer Detection. In ICDM. IEEE Computer Society, 1242--1247.Google Scholar
- Guan Wang, Sihong Xie, Bing Liu, and Philip S. Yu. 2012. Identify Online Store Review Spammers via Social Review Graph. ACM Trans. Intell. Syst. Technol. 3, 4 (2012), 61:1--61:21.Google ScholarDigital Library
- YanlingWang, Jing Zhang, Shasha Guo, Hongzhi Yin, Cuiping Li, and Hong Chen. 2021. Decoupling Representation Learning and Classification for GNN-based Anomaly Detection. In SIGIR. ACM, 1239--1248.Google Scholar
- Yanling Wang, Jing Zhang, Haoyang Li, Yuxiao Dong, Hongzhi Yin, Cuiping Li, and Hong Chen. [n.d.].Google Scholar
- Yaochen Xie, Zhao Xu, ZhengyangWang, and Shuiwang Ji. 2021. Self-Supervised Learning of Graph Neural Networks: A Unified Review. CoRR abs/2102.10757 (2021).Google Scholar
- Zhang Xinyi and Lihui Chen. 2019. Capsule Graph Neural Network. In ICLR. OpenReview.net.Google Scholar
- Keyulu Xu,Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In ICLR. OpenReview.net.Google Scholar
- Jinyu Yang, Peilin Zhao, Yu Rong, Chaochao Yan, Chunyuan Li, Hehuan Ma, and Junzhou Huang. 2021. Hierarchical Graph Capsule Network. In AAAI. AAAI Press, 10603--10611.Google Scholar
- Rui Yang,Wenrui Dai, Chenglin Li, Junni Zou, and Hongkai Xiong. 2020. NCGNN: Node-level Capsule Graph Neural Network. CoRR abs/2012.03476 (2020).Google Scholar
- Yuning You, Tianlong Chen, Yang Shen, and Zhangyang Wang. 2021. Graph Contrastive Learning Automated. In ICML (Proceedings of Machine Learning Research), Vol. 139. PMLR, 12121--12132.Google Scholar
- Tong Zhao, Tianwen Jiang, Neil Shah, and Meng Jiang. 2022. A Synergistic Approach for Graph Anomaly Detection With Pattern Mining and Feature Learning. IEEE Trans. Neural Networks Learn. Syst. 33, 6 (2022), 2393--2405.Google ScholarCross Ref
- Xiangping Zheng, Xun Liang, Bo Wu, Yuhui Guo, and Xuan Zhang. 2022. Graph Capsule Network with a Dual Adaptive Mechanism. In SIGIR. ACM, 1859--1864.Google ScholarDigital Library
- Yu Zheng, Ming Jin, Yixin Liu, Lianhua Chi, Khoa T. Phan, and Yi-Ping Phoebe Chen. 2021. Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection. CoRR abs/2108.09896 (2021).Google Scholar
- Yulin Zhu, Yuni Lai, Kaifa Zhao, Xiapu Luo, Mingquan Yuan, Jian Ren, and Kai Zhou. 2021. BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection. CoRR abs/2106.09989 (2021).Google Scholar
Index Terms
- Friend or Foe? Mining Suspicious Behavior via Graph Capsule Infomax Detector against Fraudsters
Recommendations
Decoupling Representation Learning and Classification for GNN-based Anomaly Detection
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalGNN-based anomaly detection has recently attracted considerable attention. Existing attempts have thus far focused on jointly learning the node representations and the classifier for detecting the anomalies. Inspired by the recent advances of self-...
Discriminative Graph-Level Anomaly Detection via Dual-Students-Teacher Model
Advanced Data Mining and ApplicationsAbstractDifferent from the current node-level anomaly detection task, the goal of graph-level anomaly detection is to find abnormal graphs that significantly differ from others in a graph set. Due to the scarcity of research on the work of graph-level ...
Discovering suspicious behavior in multilayer social networks
Discovering suspicious and illicit behavior in social networks is a significant problem in social network analysis. The patterns of interactions of suspicious users are quite different from their peers and can be identified by using anomaly detection ...
Comments