ABSTRACT
Graph-level anomaly detection aims at capturing anomalous individual graphs in a graph set. Due to its significance in various real-world application fields, e.g., identifying rare molecules in chemistry and detecting potential frauds in online social networks, graph-level anomaly detection has received great attention recently. In distinction from node- and edge-level anomaly detection that is devoted to identifying anomalies on a single graph, graph-level anomaly detection faces more significant challenges because both the intra- and inter- graph structural and attribute patterns need to be taken into account to distinguish anomalies that exhibit deviating structures, rare attributes or the both. Although deep graph representation learning shows effectiveness in fusing high-level representations and capturing characters of individual graphs, most of the existing works are defective in graph-level anomaly detection because of their limited capability in exploring information across graphs, the imbalanced data distribution of anomalies, and low interpretability of the black-box graph neural networks (GNNs). To overcome these limitations, we propose a novel deep evolutionary graph mapping framework named GmapAD1, which can adaptively map each graph into a new feature space based on its similarity to a set of representative nodes chosen from the graph set. By automatically adjusting the candidate nodes using a specially designed evolutionary algorithm, anomalies and normal graphs are mapped to separate areas in the new feature space where a clear boundary between them can be learned. The selected candidate nodes can therefore be regarded as a benchmark for explaining anomalies because anomalies are more dissimilar/similar to the benchmark than normal graphs. Through our extensive experiments on nine real-world datasets, we demonstrate that exploring both intra- and inter- graph structural and attribute information is critical to spot anomalous graphs, and our method has achieved statistically significant improvements compared to the state of the art in terms of precision, recall, F1 score, and AUC.
Supplemental Material
- Mohamad Faiz Ahmad, Nor Ashidi Mat Isa, Wei Hong Lim, and Koon Meng Ang. 2021. Differential evolution: A recent review based on state-of-the-art works. Alexandria Engineering Journal (2021).Google Scholar
- Leman Akoglu, Hanghang Tong, and Danai Koutra. 2015. Graph based anomaly detection and description: a survey. Data Mining and Knowledge Discovery, Vol. 29, 3 (2015), 626--688.Google ScholarDigital Library
- Jinheon Baek, Minki Kang, and Sung Ju Hwang. 2021. Accurate Learning of Graph Representations with Graph Multiset Pooling. In International Conference on Learning Representations.Google Scholar
- Sambaran Bandyopadhyay, Saley Vishal Vivek, and MN Murty. 2020. Outlier resistant unsupervised deep architectures for attributed network embedding. In the 13th International Conference on Web Search and Data Mining. 25--33.Google ScholarDigital Library
- Richard Bellman. 1966. Dynamic programming. Science, Vol. 153, 3731 (1966), 34--37.Google Scholar
- Chen Cai and Yusu Wang. 2018. A simple yet effective baseline for non-attributed graph classification. arXiv preprint arXiv:1811.03508 (2018).Google Scholar
- Chih-Chung Chang and Chih-Jen Lin. 2011. LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 2, 3 (2011), 1--27.Google ScholarDigital Library
- Wu Deng, Shifan Shang, Xing Cai, Huimin Zhao, Yingjie Song, and Junjie Xu. 2021. An improved differential evolution algorithm and its application in optimization problem. Soft Computing, Vol. 25, 7 (2021), 5277--5298.Google ScholarDigital Library
- Kaize Ding, Zhe Xu, Hanghang Tong, and Huan Liu. 2022. Data augmentation for deep graph learning: A survey. ACM SIGKDD Explorations Newsletter, Vol. 24, 2 (2022), 61--77.Google ScholarDigital Library
- 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 Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 315--324.Google ScholarDigital Library
- Dongsheng Duan, Lingling Tong, Yangxi Li, Jie Lu, Lei Shi, and Cheng Zhang. 2020. AANE: Anomaly aware network embedding for anomalous link detection. In 2020 IEEE International Conference on Data Mining (ICDM). IEEE, 1002--1007.Google ScholarCross Ref
- Claudio Gallicchio and Alessio Micheli. 2020a. Fast and deep graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 3898--3905.Google ScholarCross Ref
- Claudio Gallicchio and Alessio Micheli. 2020b. Ring reservoir neural networks for graphs. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--7.Google ScholarCross Ref
- Hongyang Gao and Shuiwang Ji. 2019. Graph U-Nets. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97). PMLR, 2083--2092.Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, Vol. 30 (2017).Google Scholar
- Jun He and Xinghuo Yu. 2001. Conditions for the convergence of evolutionary algorithms. Journal of Systems Architecture, Vol. 47, 7 (2001), 601--612.Google ScholarDigital Library
- Heivet Hernández-Pérez, Jason Mikiel-Hunter, David McAlpine, Sumitrajit Dhar, Sriram Boothalingam, Jessica JM Monaghan, and Catherine M McMahon. 2021. Understanding degraded speech leads to perceptual gating of a brainstem reflex in human listeners. PLoS Biology, Vol. 19, 10 (2021), e3001439.Google ScholarCross Ref
- Zhongbo Hu, Shengwu Xiong, Qinghua Su, and Xiaowei Zhang. 2013. Sufficient conditions for global convergence of differential evolution algorithm. Journal of Applied Mathematics, Vol. 2013 (2013).Google ScholarCross Ref
- Jarmo Ilonen, Joni-Kristian Kamarainen, and Jouni Lampinen. 2003. Differential evolution training algorithm for feed-forward neural networks. Neural Processing Letters, Vol. 17, 1 (2003), 93--105.Google ScholarDigital Library
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.Google Scholar
- Junhyun Lee, Inyeop Lee, and Jaewoo Kang. 2019. Self-Attention Graph Pooling. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97). PMLR, 3734--3743.Google Scholar
- Fanzhen Liu, Xiaoxiao Ma, Jia Wu, Jian Yang, Shan Xue, Amin Behesht, Chuan Zhou, Hao Peng, Quan Z. Sheng, and Charu Aggarwal. 2022. DAGAD: Data Augmentation for Graph Anomaly Detection. In Proceedings of the IEEE International Conference on Data Mining.Google ScholarCross Ref
- Rongrong Ma, Guansong Pang, Ling Chen, and Anton van den Hengel. 2022a. Deep graph-level anomaly detection by glocal knowledge distillation. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining. 704--714.Google Scholar
- 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 Transactions on Knowledge and Data Engineering (2021), (Early Access).Google ScholarDigital Library
- Xiaoxiao Ma, Shan Xue, Jia Wu, Jian Yang, Cecile Paris, Surya Nepal, and Quan Z Sheng. 2022b. Deep Multi-Attributed-View Graph Representation Learning. IEEE Transactions on Network Science and Engineering, Vol. 9, 5 (2022), 3762--3774.Google ScholarCross Ref
- Caleb C Noble and Diane J Cook. 2003. Graph-based anomaly detection. In Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 631--636.Google ScholarDigital Library
- Shirui Pan, Jia Wu, Xingquan Zhu, Guodong Long, and Chengqi Zhang. 2016. Task sensitive feature exploration and learning for multitask graph classification. IEEE Transactions on Cybernetics, Vol. 47, 3 (2016), 744--758.Google ScholarCross Ref
- Guansong Pang, Chunhua Shen, Longbing Cao, and Anton Van Den Hengel. 2021. Deep learning for anomaly detection: A review. ACM Computing Surveys (CSUR), Vol. 54, 2 (2021), 1--38.Google ScholarDigital Library
- A Kai Qin, Vicky Ling Huang, and Ponnuthurai N Suganthan. 2008. Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Ttransactions on Evolutionary Computation, Vol. 13, 2 (2008), 398--417.Google ScholarDigital Library
- Chen Qiu, Marius Kloft, Stephan Mandt, and Maja Rudolph. 2022. Raising the Bar in Graph-level Anomaly Detection. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22. 2196--2203.Google ScholarCross Ref
- Günter Rudolph. 1994. Convergence analysis of canonical genetic algorithms. IEEE Transactions on Neural Networks, Vol. 5, 1 (1994), 96--101.Google ScholarDigital Library
- Günter Rudolph. 1996. Convergence of evolutionary algorithms in general search spaces. In IEEE International Conference on Evolutionary Computation. 50--54.Google ScholarCross Ref
- Rainer Storn and Kenneth Price. 1997. Differential evolution--a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, Vol. 11, 4 (1997), 341--359.Google ScholarDigital Library
- Jianheng Tang, Jiajin Li, Ziqi Gao, and Jia Li. 2022. Rethinking Graph Neural Networks for Anomaly Detection. In International Conference on Machine Learning.Google Scholar
- Matteo Togninalli, Elisabetta Ghisu, Felipe Llinares-López, Bastian Rieck, and Karsten Borgwardt. 2019. Wasserstein Weisfeiler-Lehman Graph Kernels. In Advances in Neural Information Processing Systems 32 (NeurIPS). Curran Associates, Inc., 6436--6446.Google Scholar
- Martijn P Van Den Heuvel and Hilleke E Hulshoff Pol. 2010. Exploring the brain network: a review on resting-state fMRI functional connectivity. European Neuropsychopharmacology, Vol. 20, 8 (2010), 519--534.Google ScholarCross Ref
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In International Conference on Learning Representations.Google Scholar
- Jakob Vesterstrom and Rene Thomsen. 2004. A comparative study of differential evolution, particle swarm optimization, and evolutionary algorithms on numerical benchmark problems. In Proceedings of the 2004 Congress on Evolutionary Computation, Vol. 2. IEEE, 1980--1987.Google ScholarCross Ref
- Jia Wu and Zhihua Cai. 2014. A naive Bayes probability estimation model based on self-adaptive differential evolution. Journal of Intelligent Information Systems, Vol. 42, 3 (2014), 671--694.Google ScholarDigital Library
- Jia Wu, Shirui Pan, Xingquan Zhu, Chengqi Zhang, and Xindong Wu. 2018. Multi-instance learning with discriminative bag mapping. IEEE Transactions on Knowledge and Data Engineering, Vol. 30, 6 (2018), 1065--1080.Google ScholarCross Ref
- Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, Vol. 32, 1 (2020), 4--24.Google ScholarCross Ref
- Keyulu Xu, Weihua Hu, Jure Leskovec, and Stefanie Jegelka. 2019. How Powerful are Graph Neural Networks?. In International Conference on Learning Representations.Google Scholar
- Zhitao Ying, Jiaxuan You, Christopher Morris, Xiang Ren, Will Hamilton, and Jure Leskovec. 2018. Hierarchical graph representation learning with differentiable pooling. Advances in Neural Information Processing Systems, Vol. 31 (2018).Google Scholar
- Wenchao Yu, Wei Cheng, Charu C Aggarwal, Kai Zhang, Haifeng Chen, and Wei Wang. 2018. Netwalk: A flexible deep embedding approach for anomaly detection in dynamic networks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2672--2681.Google ScholarDigital Library
- Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. 2022. Explainability in graph neural networks: A taxonomic survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022).Google Scholar
- Ge Zhang, Jia Wu, Jian Yang, Amin Beheshti, Shan Xue, Chuan Zhou, and Quan Z Sheng. 2021. FRAUDRE: fraud detection dual-resistant to graph inconsistency and imbalance. In 2021 IEEE International Conference on Data Mining (ICDM). IEEE, 867--876.Google ScholarCross Ref
- Ge Zhang, Zhenyu Yang, Jia Wu, Jian Yang, Shan Xue, Hao Peng, Jianlin Su, Chuan Zhou, Quan Z Sheng, Leman Akoglu, et al. 2022. Dual-discriminative graph neural network for imbalanced graph-level anomaly detection. Advances in Neural Information Processing Systems, Vol. 35 (2022), 24144--24157.Google Scholar
- Yongshan Zhang, Jia Wu, Chuan Zhou, Peng Zhang, and Zhihua Cai. 2016. Multiple-instance learning with evolutionary instance selection. In International Conference on Database Systems for Advanced Applications. Springer, 229--241.Google ScholarCross Ref
- Lingxiao Zhao and Leman Akoglu. 2021. On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights. Big Data (2021).Google Scholar
- Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, and Liang Wang. 2021. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021. 2069--2080.Google ScholarDigital Library
Index Terms
- Towards Graph-level Anomaly Detection via Deep Evolutionary Mapping
Recommendations
Multi-representations Space Separation based Graph-level Anomaly-aware Detection
SSDBM '23: Proceedings of the 35th International Conference on Scientific and Statistical Database ManagementGraph structure patterns are widely used to model different area data recently. How to detect anomalous graph information on these graph data has become a popular research problem. The objective of this research is centered on the particular issue that ...
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 ...
One-class graph neural networks for anomaly detection in attributed networks
AbstractNowadays, graph-structured data are increasingly used to model complex systems. Meanwhile, detecting anomalies from graph has become a vital research problem of pressing societal concerns. Anomaly detection is an unsupervised learning task of ...
Comments