Abstract
Graph-level anomaly detection aims to identify abnormal graphs that exhibit deviant structures and node attributes compared to the majority in a graph set. One primary challenge is to learn normal patterns manifested in both fine-grained and holistic views of graphs for identifying graphs that are abnormal in part or in whole. To tackle this challenge, we propose a novel approach called Hierarchical Memory Networks (HimNet), which learns hierarchical memory modules—node and graph memory modules—via a graph autoencoder network architecture. The node-level memory module is trained to model fine-grained, internal graph interactions among nodes for detecting locally abnormal graphs, while the graph-level memory module is dedicated to the learning of holistic normal patterns for detecting globally abnormal graphs. The two modules are jointly optimized to detect both locally- and globally-anomalous graphs. Extensive empirical results on 16 real-world graph datasets from various domains show that i) HimNet significantly outperforms the state-of-art methods and ii) it is robust to anomaly contamination. Codes are available at: https://github.com/Niuchx/HimNet.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
All the graph datasets are available on https://chrsmrrs.github.io/datasets/docs/datasets/ except hERG which is obtained from https://tdcommons.ai/single_pred_tasks/tox/.
References
Aggarwal, C.C., Wang, H.: Graph data management and mining: a survey of algorithms and applications. In: Managing and Mining Graph Data, pp. 13–68. Springer, Boston (2010). https://doi.org/10.1007/978-1-4419-6045-0_2
Akoglu, L., Tong, H., Koutra, D.: Graph based anomaly detection and description: a survey. Data Mining Knowl. Discov. 29, 626–688 (2015)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. 19 (2006)
Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: Lof: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104 (2000)
Campos, G.O., et al.: On the evaluation of unsupervised outlier detection: measures, datasets, and an empirical study. Data Mining Knowl. Discov. 30, 891–927 (2016)
Chen, J., Sathe, S., Aggarwal, C., Turaga, D.: Outlier detection with autoencoder ensembles. In: Proceedings of the 2017 SIAM International Conference on Data Mining, pp. 90–98. SIAM (2017)
Ding, K., Li, J., Agarwal, N., Liu, H.: Inductive anomaly detection on attributed networks. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 1288–1294 (2021)
Gong, D., et al.: Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1705–1714 (2019)
**, M., Liu, Y., Zheng, Y., Chi, L., Li, Y.F., Pan, S.: Anemone: graph anomaly detection with multi-scale contrastive learning. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 3122–3126 (2021)
Kim, Y., Kim, M., Kim, G.: Memorization precedes generation: learning unsupervised GANs with memory networks. In: International Conference on Learning Representations (2018)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. ar**v preprint ar**v:1312.6114 (2013)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. ar**v preprint ar**v:1611.07308 (2016)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (2017)
Kumagai, A., Iwata, T., Fujiwara, Y.: Semi-supervised anomaly detection on attributed graphs. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2021)
Lee, C.Y., Chen, Y.P.P.: Descriptive prediction of drug side-effects using a hybrid deep learning model. Int. J. Intell. Syst. 36(6), 2491–2510 (2021)
Li, C., Zhu, J., Zhang, B.: Learning to generate with memory. In: International Conference on Machine Learning, pp. 1177–1186. PMLR (2016)
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422. IEEE (2008)
Liu, Y., Ding, K., Liu, H., Pan, S.: Good-d: on unsupervised graph out-of-distribution detection. In: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pp. 339–347 (2023)
Liu, Y., Li, Z., Pan, S., Gong, C., Zhou, C., Karypis, G.: Anomaly detection on attributed networks via contrastive self-supervised learning. IEEE Trans. Neural Netw. Learn. Syst. 33(6), 2378–2392 (2021)
Luo, X., et al.: Deep graph level anomaly detection with contrastive learning. Sci. Rep. 12(1), 19867 (2022)
Ma, R., Pang, G., Chen, L., van den Hengel, A.: Deep graph-level anomaly detection by glocal knowledge distillation. In: The Fifteenth ACM International Conference on Web Search and Data Mining (WSDM 2022) (2022)
Narayanan, A., Chandramohan, M., Venkatesan, R., Chen, L., Liu, Y., Jaiswal, S.: graph2vec: learning distributed representations of graphs. ar**v preprint ar**v:1707.05005 (2017)
Neumann, M., Garnett, R., Bauckhage, C., Kersting, K.: Propagation kernels: efficient graph kernels from propagated information. Mach. Learn. 102, 209–245 (2016)
Pang, G., Shen, C., Cao, L., Hengel, A.V.D.: Deep learning for anomaly detection: a review. ACM Comput. Surv. 54(2), 1–38 (2021)
Pang, G., Shen, C., van den Hengel, A.: Deep anomaly detection with deviation networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 353–362 (2019)
Pang, G., Ting, K.M., Albrecht, D.: Lesinn: detecting anomalies by identifying least similar nearest neighbours. In: 2015 IEEE International Conference on Data Mining Workshop (ICDMW), pp. 623–630. IEEE (2015)
Park, H., Noh, J., Ham, B.: Learning memory-guided normality for anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14372–14381 (2020)
Qiao, H., Pang, G.: Truncated affinity maximization: one-class homophily modeling for graph anomaly detection. ar**v preprint ar**v:2306.00006 (2023)
Qiu, C., Kloft, M., Mandt, S., Rudolph, M.: Raising the bar in graph-level anomaly detection. ar**v preprint ar**v:2205.13845 (2022)
Ruff, L., et al.: Deep one-class classification. In: International Conference on Machine Learning, pp. 4393–4402. PMLR (2018)
Schölkopf, B., Williamson, R.C., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. Adv. Neural Inf. Process. Syst. 12 (1999)
Shervashidze, N., Schweitzer, P., Van Leeuwen, E.J., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-lehman graph kernels. J. Mach. Learn. Res. 12(9) (2011)
Sun, F.Y., Hoffman, J., Verma, V., Tang, J.: Infograph: unsupervised and semi-supervised graph-level representation learning via mutual information maximization. In: International Conference on Learning Representations (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lió, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)
Wang, Q., Pang, G., Salehi, M., Buntine, W., Leckie, C.: Cross-domain graph anomaly detection via anomaly-aware contrastive alignment. ar**v preprint ar**v:2212.01096 (2022)
Weston, J., Chopra, S., Bordes, A.: Memory networks. In: International Conference on Learning Representations (2015)
Woolson, R.F.: Wilcoxon signed-rank test. In: Wiley Encyclopedia of Clinical Trials, pp. 1–3 (2007)
Wu, Z., **ong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733–3742 (2018)
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., Philip, S.Y.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2020)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? In: International Conference on Learning Representations (2019)
Zhai, S., Cheng, Y., Lu, W., Zhang, Z.: Deep structured energy based models for anomaly detection. In: International Conference on Machine Learning, pp. 1100–1109. PMLR (2016)
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. Adv. Neural Inf. Process. Syst. 31 (2018)
Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Zhang, Z., Cui, P., Zhu, W.: Deep learning on graphs: a survey. IEEE Trans. Knowl. Data Eng. 34(1), 249–270 (2020)
Zhao, L., Akoglu, L.: On using classification datasets to evaluate graph outlier detection: peculiar observations and new insights. Big Data (2021)
Zhou, C., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 665–674 (2017)
Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)
Acknowledgment
This work is partially supported by Australian Research Council under Grant DP210101347.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
In this work, we study the problem of graph-level anomaly detection which aims to identify abnormal graphs that exhibit unusual patterns in comparison to the majority in a graph set. Since graphs are widely used in various domains, anomaly detection on graphs has broad applications, such as identifying toxic molecules from chemical compound graphs and recognizing abnormal internet activity graphs. To capture the hierarchical normal patterns of graph data, we propose hierarchical memory networks to learn node and graph memory modules. The proposed method enables the detection of both locally and globally anomalous graphs. For all the used data sets in this paper, there is no private personally identifiable information or offensive content. However, when using the proposed method for solving realistic problems, it is essential to ensure that appropriate measures are taken to protect the privacy of individuals. This may include anonymizing data, limiting access to sensitive information, or obtaining informed consent from individuals before collecting their data.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Niu, C., Pang, G., Chen, L. (2023). Graph-Level Anomaly Detection via Hierarchical Memory Networks. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14169. Springer, Cham. https://doi.org/10.1007/978-3-031-43412-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-43412-9_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43411-2
Online ISBN: 978-3-031-43412-9
eBook Packages: Computer ScienceComputer Science (R0)