[go: up one dir, main page]
Skip to main content
SpringerLink
Log in

A graph attention network-based model for anomaly detection in multivariate time series

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Anomaly detection of multivariate time series plays a growingly crucial role in intelligent operation and maintenance. Most existing anomaly detection models tend to focus on extracting temporal information while essentially ignoring the relationships among multiple sensors. Graph neural networks simulate multivariate inter-series relationships but suffer from the independent updating of graph structure from data. To overcome such limitation, we present a graph attention network-based model to learn the sensors relationships. It is equipped with a sustainable updating similarity-constrained graph structure learning method and a time series encoder. The graph learning method performs continuous updating of the graph structure. The encoder generates augmented and representative views along the temporal dimension. Our proposed model not only efficiently learns sensor relationships but also improves the ability of anomaly detection. Experiments are performed on publicly benchmark datasets, including SWaT, WADI, and HAI, with F1 scores of 92.98%, 91.19%, and 87.12%, respectively. This confirms that the proposed model outperforms the state-of-the-art in anomaly detection performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Algorithm 1
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability

Data will be made available on request.

References

  1. Zhang Z, Li W, Ding W et al (2022) STAD-GAN: unsupervised anomaly detection on multivariate time series with self-training generative adversarial networks. ACM Trans Knowl Discov Data 17(5):1–18. https://doi.org/10.1145/3572780

    Article  Google Scholar 

  2. Zeng Z, Xiao R, Lin X et al (2023) Double locality sensitive hashing bloom filter for high-dimensional streaming anomaly detection. Inf Process Manag 60(3):103306. https://doi.org/10.1016/j.ipm.2023.103306

    Article  Google Scholar 

  3. Blázquez-García A, Conde A, Mori U et al (2021) A review on outlier/anomaly detection in time series data. ACM Comput Surv 54(3):1–33. https://doi.org/10.1145/3444690

    Article  Google Scholar 

  4. Yin C, Zhang S, Wang J et al (2020) Anomaly detection based on convolutional recurrent autoencoder for IoT time series. IEEE Trans Syst Man Cybern: Syst 52(1):112–122. https://doi.org/10.1109/TSMC.2020.2968516

    Article  Google Scholar 

  5. Douiba M, Benkirane S, Guezzaz A et al (2023) An improved anomaly detection model for IoT security using decision tree and gradient boosting. J Supercomput 79(3):3392–3411. https://doi.org/10.1007/s11227-022-04783-y

    Article  Google Scholar 

  6. Zong B, Song Q, Min MR, et al (2018) Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations, 1–19, https://openreview.net/forum?id=BJJLHbb0-

  7. Audibert J, Michiardi P, Guyard F, et al (2020) USAD: unsupervised anomaly detection on multivariate time series. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 3395–3404, https://doi.org/10.1145/3394486.3403392

  8. Li D, Chen D, Jin B, et al (2019) MAD-GAN: multivariate anomaly detection for time series data with generative adversarial networks. In: Text and Time Series: 28th International Conference on Artificial Neural Networks, 703–716, https://doi.org/10.1007/978-3-030-30490-4_56

  9. Park D, Hoshi Y, Kemp CC (2018) A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder. IEEE Robotics and Automation Letters 3(3):1544–1551. https://doi.org/10.1109/LRA.2018.2801475

    Article  Google Scholar 

  10. Zhou L, Zeng Q, Li B (2022) Hybrid anomaly detection via multihead dynamic graph attention networks for multivariate time series. IEEE Access 10:40967–40978. https://doi.org/10.1109/ACCESS.2022.3167640

    Article  Google Scholar 

  11. Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations, 1–14, https://openreview.net/forum?id=SJU4ayYgl

  12. Veličković P, Cucurull G, Casanova A, et al (2018) Graph attention networks. In: International Conference on Learning Representations, 1–12, https://openreview.net/forum?id=rJXMpikCZ

  13. Zhao H, Wang Y, Duan J, et al (2020) Multivariate time-series anomaly detection via graph attention network. In: 2020 IEEE International Conference on Data Mining, IEEE, 841–850, https://doi.org/10.1109/ICDM50108.2020.00093

  14. Deng A, Hooi B (2021) Graph neural network-based anomaly detection in multivariate time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, 4027–4035, https://doi.org/10.1609/aaai.v35i5.16523

  15. Zhan J, Wang S, Ma X, et al (2022) STGAT-MAD: Spatial-temporal graph attention network for multivariate time series anomaly detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 3568–3572, https://doi.org/10.1109/ICASSP43922.2022.9747274

  16. Tang C, Xu L, Yang B, et al (2023) GRU-based interpretable multivariate time series anomaly detection in industrial control system. Comput Secur, p 103094. https://doi.org/10.1016/j.cose.2023.103094

  17. Naito S, Taguchi Y, Nakata K, et al (2021) Anomaly detection for multivariate time series on large-scale fluid handling plant using two-stage autoencoder. In: 2021 International Conference on Data Mining Workshops (ICDMW), IEEE, 542–551

  18. Fährmann D, Damer N, Kirchbuchner F et al (2022) Lightweight long short-term memory variational auto-encoder for multivariate time series anomaly detection in industrial control systems. Sensors 22(8):2886

    Article  Google Scholar 

  19. Zeng F, Chen M, Qian C et al (2023) Multivariate time series anomaly detection with adversarial transformer architecture in the internet of things. Futur Gener Comput Syst 144:244–255

    Article  Google Scholar 

  20. Wu S, Sun F, Zhang W et al (2022) Graph neural networks in recommender systems: a survey. ACM Comput Surv 55(5):1–37. https://doi.org/10.1145/3535101

    Article  Google Scholar 

  21. Zhang M, Wu S, Yu X et al (2022) Dynamic graph neural networks for sequential recommendation. IEEE Trans Knowl Data Eng 01:1–12. https://doi.org/10.1109/TKDE.2022.3151618

    Article  Google Scholar 

  22. Kumari A, Sahoo SP, Behera RK, et al (2020) Supervised machine learning for link prediction using path-based similarity features. In: 2020 IEEE 17th India Council International Conference (INDICON), IEEE, 1–7

  23. Kumari A, Behera RK, Sahoo B, et al (2022) Prediction of link evolution using community detection in social network. Computing, 1–22

  24. Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271https://doi.org/10.48550/arXiv.1803.01271

  25. Shin HK, Lee W, Yun JH, et al (2020) Hai 1.0: Hil-based augmented ics security dataset. In: Proceedings of the 13th USENIX Conference on Cyber Security Experimentation and Test, 1–5

  26. Xu H, Chen W, Zhao N, et al (2018) Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications. In: Proceedings of the 2018 World Wide Web Conference, 187–196, https://doi.org/10.1145/3178876.3185996

  27. Su Y, Zhao Y, Niu C, et al (2019) Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 2828–2837, https://doi.org/10.1145/3292500.3330672

  28. Li Z, Zhao Y, Han J, et al (2021) Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 3220–3230, https://doi.org/10.1145/3447548.3467075

  29. Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International Conference on Learning Representations, 1–15. https://doi.org/10.48550/arXiv.1412.6980

  30. Chen Z, Chen D, Zhang X et al (2021) Learning graph structures with transformer for multivariate time-series anomaly detection in IoT. IEEE Internet Things J 9(12):9179–9189. https://doi.org/10.1109/JIOT.2021.3100509

    Article  MathSciNet  Google Scholar 

  31. Han S, Woo SS (2022) Learning sparse latent graph representations for anomaly detection in multivariate time series. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2977–2986, https://doi.org/10.1145/3534678.3539117

  32. Cieslak MC, Castelfranco AM, Roncalli V et al (2020) t-distributed stochastic neighbor embedding (t-SNE): a tool for eco-physiological transcriptomic analysis. Mar Genomics 51:100723. https://doi.org/10.1016/j.margen.2019.100723

    Article  Google Scholar 

Download references

Funding

The authors would appreciate the support from the Major National Science and Technology Special Projects (2016ZX02301003-004-007) and the Natural Science Foundation of Hebei Province (F2020202067).

Author information

Authors and Affiliations

  1. School of Electronic and Information Engineering, Hebei University of Technology, No. 5340, Xiping Road, Tianjin, 300401, Tianjin, China

    Wei Zhang & Fan Yang

  2. School of Artificial Intelligence, Hebei University of Technology, No. 5340, Xiping Road, Tianjin, 300401, Tianjin, China

    Ping He & Chuntian Qin

  3. School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, Chengdu, 611731, Sichuan, China

    Ying Liu

Authors
  1. Wei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ping He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chuntian Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ying Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ping He.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, W., He, P., Qin, C. et al. A graph attention network-based model for anomaly detection in multivariate time series. J Supercomput 80, 8529–8549 (2024). https://doi.org/10.1007/s11227-023-05772-5

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-023-05772-5

Keywords

Search

Navigation