skip to main content
10.1145/3488560.3498389acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article

ComGA: Community-Aware Attributed Graph Anomaly Detection

Published: 15 February 2022 Publication History

Abstract

Graph anomaly detection, here, aims to find rare patterns that are significantly different from other nodes. Attributed graphs containing complex structure and attribute information are ubiquitous in our life scenarios such as bank account transaction graph and paper citation graph. Anomalous nodes on attributed graphs show great difference from others in the perspectives of structure and attributes, and give rise to various types of graph anomalies. In this paper, we investigate three types of graph anomalies: local, global, and structure anomalies. And, graph neural networks (GNNs) based anomaly detection methods attract considerable research interests due to the power of modeling attributed graphs. However, the convolution operation of GNNs aggregates neighbors information to represent nodes, which makes node representations more similar and cannot effectively distinguish between normal and anomalous nodes, thus result in sub-optimal results. To improve the performance of anomaly detection, we propose a novel community-aware attributed graph anomaly detection framework (ComGA). We design a tailored deep graph convolutional network (tGCN) to anomaly detection on attributed graphs. Extensive experiments on eight real-life graph datasets demonstrate the effectiveness of ComGA.

Supplementary Material

MP4 File (WSDM22-fp157.mp4)
This work aims to design a community-aware attributed graph anomaly detection framework, which can learn distinguishable node representations for local, global, and structure anomalies. The framework consists of three major modules. Community detection module is to construct the modularity matrix of the given graph, and then utilize the deep autoencoder to learn community-specific representations of nodes. tGCN module is to employ the GCN model to encode the attributed graph, and propagate community-specific representations into its corresponding layers of GCN via multiple gateways. Anomaly detection module is to design two decoders to reconstruct graph structure and attribute information from anomaly-aware node representations, and then the joint reconstruction errors are used to detect anomalous nodes.

References

[1]
Leman Akoglu, Hanghang Tong, Brendan Meeder, and Christos Faloutsos. 2012. PICS: Parameter-free Identification of Cohesive Subgroups in Large Attributed Graphs. In SDM. 439--450.
[2]
Deyu Bo, Xiao Wang, Chuan Shi, Meiqi Zhu, Emiao Lu, and Peng Cui. 2020. Structural Deep Clustering Network. In WWW. 1400--1410.
[3]
Bernardo Branco, Pedro Abreu, Ana Sofia Gomes, Mariana SC Almeida, João Tiago Ascensão, and Pedro Bizarro. 2020. Interleaved sequence rnns for fraud detection. In KDD. 3101--3109.
[4]
Markus M Breunig, Hanspeter Kriegel, Raymond T Ng, and Jorg Sander. 2000. LOF: identifying density-based local outliers. In ACM SIGMOD Rec, Vol. 29. 93-- 104.
[5]
Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive Universal Generalized PageRank Graph Neural Network. In ICLR.
[6]
Kaize Ding, Jundong Li, Nitin Agarwal, and Huan Liu. 2020. Inductive Anomaly Detection on Attributed Networks. In IJCAI. 1288--1294.
[7]
Kaize Ding, Jundong Li, Rohit Bhanushali, and Huan Liu. 2019. Deep Anomaly Detection on Attributed Networks. In SDM. 594--602.
[8]
Haoyi Fan, Fengbin Zhang, and Zuoyong Li. 2020. AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks. In ICASSP. 5685--5689.
[9]
Jing Gao, Feng Liang, Wei Fan, Chi Wang, Yizhou Sun, and Jiawei Han. 2010. On community outliers and their efficient detection in information networks. In KDD. 813--822.
[10]
William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In NIPS. 1024--1034.
[11]
Tianjin Huang, Yulong Pei, Vlado Menkovski, and Mykola Pechenizkiy. 2021. Hop-count based self-supervised anomaly detection on attributed networks. arXiv preprint arXiv:2104.07917 (2021).
[12]
Xiao Huang, Jundong Li, and Xia Hu. 2017. Label Informed Attributed Network Embedding. In WSDM. 731--739.
[13]
Di Jin, Zheng Chen, Dongxiao He, and Weixiong Zhang. 2015. Modeling with node degree preservation can accurately find communities. In AAAI.
[14]
Diederik P Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980 (2014).
[15]
Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.
[16]
Jundong Li, Harsh Dani, Xia Hu, and Huan Liu. 2017. Radar: Residual Analysis for Anomaly Detection in Attributed Networks. In IJCAI. 2152--2158.
[17]
Jundong Li, Ruocheng Guo, Chenghao Liu, and Huan Liu. 2019. Adaptive Unsupervised Feature Selection on Attributed Networks. In KDD. 92--100.
[18]
Qimai Li, Zhichao Han, and Xiaoming Wu. 2018. Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning. In AAAI. 3538--3545.
[19]
Yuening Li, Xiao Huang, Jundong Li, Mengnan Du, and Na Zou. 2019. SpecAE: Spectral AutoEncoder for Anomaly Detection in Attributed Networks. In CIKM. 2233--2236.
[20]
Fanzhen Liu, Zhao Li, Baokun Wang, Jia Wu, Jian Yang, Jiaming Huang, Yiqing Zhang, Weiqiang Wang, Surya Nepal, and Quanzheng Sheng. 2022. eRiskCom: An e-commerce risky community detection platform. VLDBJ (2022).
[21]
Fanzhen Liu, Shan Xue, Jia Wu, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Jian Yang, and Philip S. Yu. 2020. Deep learning for community detection: progress, challenges and opportunities. In IJCAI. 4981--4987.
[22]
Juan Liu, Eric A Bier, Aaron Wilson, John Alexis Guerragomez, Tomonori Honda, Kumar Sricharan, Leilani H Gilpin, and Daniel Davies. 2016. Graph Analysis for Detecting Fraud, Waste, and Abuse in Healthcare Data. Ai Magazine 37, 2 (2016), 33--46.
[23]
Yixin Liu, Zhao Li, Shirui Pan, Chen Gong, Chuan Zhou, and George Karypis. 2021. Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning. IEEE TNNLS (2021), 1--15.
[24]
Xuexiong Luo, JiaWu, Chuan Zhou, Xiankun Zhang, and YuanWang. 2020. Deep Semantic Network Representation. In ICDM. 1154--1159.
[25]
Xiaoxiao Ma, Jia Wu, Shan Xue, Jian Yang, Chuan Zhou, Quan Z Sheng, Hui Xiong, and Leman Akoglu. 2021. A comprehensive survey on graph anomaly detection with deep learning. IEEE TKDE (2021).
[26]
Emmanuel Müller, Patricia Iglesias Sánchez, Yvonne Mülle, and Klemens Böhm. 2013. Ranking outlier nodes in subspaces of attributed graphs. In ICDEWorkshops. 216--222.
[27]
M E J Newman. 2006. Modularity and community structure in networks. PNAS 103, 23 (2006), 8577--8582.
[28]
Yulong Pei, Tianjin Huang, Werner van Ipenburg, and Mykola Pechenizkiy. 2020. ResGCN: Attention-based Deep Residual Modeling for Anomaly Detection on Attributed Networks. CoRR abs/2009.14738 (2020).
[29]
Bryan Perozzi and Leman Akoglu. 2016. Scalable Anomaly Ranking of Attributed Neighborhoods. In SDM. 207--215.
[30]
Bryan Perozzi, Leman Akoglu, Patricia Iglesias Sánchez, and Emmanuel Müller. 2014. Focused clustering and outlier detection in large attributed graphs. In KDD. 1346--1355.
[31]
Patricia Iglesias Sanchez, Emmanuel Muller, Fabian Laforet, Fabian Keller, and Klemens Bohm. 2013. Statistical Selection of Congruent Subspaces for Mining Attributed Graphs. In ICDM. 647--656.
[32]
Wei Song, Heng Yin, Chang Liu, and Dawn Song. 2018. DeepMem: Learning Graph Neural Network Models for Fast and Robust Memory Forensic Analysis. In ACM CCS. 606--618.
[33]
Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, and Philip S. Yu. 2021. A Comprehensive Survey on Community Detection with Deep Learning. IEEE TNNLS (2021).
[34]
Patricia Iglesias Sánchez, Emmanuel Müller, Oretta Irmler, and Klemens Böhm. 2014. Local context selection for outlier ranking in graphs with multiple numeric node attributes. In SSDBM. 16:1--16:12.
[35]
Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In ICLR.
[36]
Teng Xiao, Zhengyu Chen, Donglin Wang, and Suhang Wang. 2021. Learning How to Propagate Messages in Graph Neural Networks. In KDD. 1894--1903.
[37]
Hongzuo Xu, Yijie Wang, Songlei Jian, Zhenyu Huang, Yongjun Wang, Ning Liu, and Fei Li. 2021. Beyond Outlier Detection: Outlier Interpretation by Attention- Guided Triplet Deviation Network. In WWW. 1328--1339.
[38]
Xiaowei Xu, Nurcan Yuruk, Zhidan Feng, and Thomas A. J. Schweiger. 2007. SCAN: A Structural Clustering Algorithm for Networks. In KDD. 824--833.
[39]
Liang Yang, Xiaochun Cao, Dongxiao He, ChuanWang, XiaoWang, andWeixiong Zhang. 2016. Modularity based community detection with deep learning. In IJCAI. 2252--2258.
[40]
Ge Zhang, Zhao Li, Jiaming Huang, Jia Wu, Chuan Zhou, and Jian Yang. 2022. eFraudCom: An E-commerce Fraud Detection System via Competitive Graph Neural Networks. ACM TOIS (2022).
[41]
Ge Zhang, JiaWu, Jian Yang, Amin Beheshti, Shan Xue, Chuan Zhou, and Michael Sheng. 2021. FRAUDRE: Fraud Detection Dual-Resistant to Graph Inconsistency and Imbalance. In ICDM.
[42]
Peng Zhen, Minnan Luo, Jundong Li, Huan Liu, and Qinghua Zheng. 2018. ANOMALOUS: A Joint Modeling Approach for Anomaly Detection on Attributed Networks. In IJCAI. 3513--3519.

Cited By

View all
  • (2025)Few-Shot Graph Anomaly Detection via Dual-Level Knowledge DistillationEntropy10.3390/e2701002827:1(28)Online publication date: 1-Jan-2025
  • (2025)SAMCL: Subgraph-Aligned Multiview Contrastive Learning for Graph Anomaly DetectionIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2023.332327436:1(1664-1676)Online publication date: Jan-2025
  • (2025)Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and ObjectivesIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.350130737:2(881-895)Online publication date: Feb-2025
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
February 2022
1690 pages
ISBN:9781450391320
DOI:10.1145/3488560
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 February 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. anomaly detection
  2. attributed graphs
  3. community structure
  4. graph neural networks

Qualifiers

  • Research-article

Funding Sources

  • the Natural Science Foundation of Tianjin
  • the Research Project of Tianjin Municipal Commission of Education
  • ARC DECRA Project
  • the National Natural Science Foundation of China
  • Tianjin Science and Technology Commissioner project

Conference

WSDM '22

Acceptance Rates

Overall Acceptance Rate 498 of 2,863 submissions, 17%

Upcoming Conference

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)491
  • Downloads (Last 6 weeks)56
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)Few-Shot Graph Anomaly Detection via Dual-Level Knowledge DistillationEntropy10.3390/e2701002827:1(28)Online publication date: 1-Jan-2025
  • (2025)SAMCL: Subgraph-Aligned Multiview Contrastive Learning for Graph Anomaly DetectionIEEE Transactions on Neural Networks and Learning Systems10.1109/TNNLS.2023.332327436:1(1664-1676)Online publication date: Jan-2025
  • (2025)Rethinking Unsupervised Graph Anomaly Detection With Deep Learning: Residuals and ObjectivesIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.350130737:2(881-895)Online publication date: Feb-2025
  • (2025)Context Correlation Discrepancy Analysis for Graph Anomaly DetectionIEEE Transactions on Knowledge and Data Engineering10.1109/TKDE.2024.348837537:1(174-187)Online publication date: Jan-2025
  • (2025)NMFAD: Neighbor-Aware Mask-Filling Attributed Network Anomaly DetectionIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.351657020(364-374)Online publication date: 1-Jan-2025
  • (2025)An Improved Reconstruction-Based Multiattribute Contrastive Learning for Digital-Twin-Enabled Industrial SystemIEEE Internet of Things Journal10.1109/JIOT.2024.348303812:4(3670-3679)Online publication date: 15-Feb-2025
  • (2025)Identifying local useful information for attribute graph anomaly detectionNeurocomputing10.1016/j.neucom.2024.128900617(128900)Online publication date: Feb-2025
  • (2025)ANOGAT-Sparse-TL: A hybrid framework combining sparsification and graph attention for anomaly detection in attributed networks using the optimized loss function incorporating the Twersky loss for improved robustnessKnowledge-Based Systems10.1016/j.knosys.2025.113144311(113144)Online publication date: Feb-2025
  • (2025)A comprehensive survey on GNN-based anomaly detection: taxonomy, methods, and the role of large language modelsInternational Journal of Machine Learning and Cybernetics10.1007/s13042-024-02516-6Online publication date: 4-Feb-2025
  • (2024)Detecting Unseen Anomalies in Dynamic GraphProceedings of the 2024 3rd International Conference on Algorithms, Data Mining, and Information Technology10.1145/3701100.3701120(93-98)Online publication date: 27-Sep-2024
  • Show More Cited By

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media