Abstract
Change point detection is an important subset of anomaly detection problems. Due to the ever-increasing volume of time-series data, detecting change points has important significance, which can find anomalies early and reduce losses, yet very challenging as it is affected by periodicity, multi-input series, and long time series. The performance of traditional methods typically scales poorly.
In this paper, we propose Trident, a novel prediction-based change point detection approach via dual-level attention learning. As the name implies, our model consists of three key modules which are the prediction, detection, and selection module. The three modules are integrated in a principled way of detecting change points more accurately and efficiently. Simulations and experiments highlight the effectiveness and efficacy of the Trident for change point detection in time series. Our approach outperforms the state-of-the-art methods on two real-world datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adams, R.P., MacKay, D.J.: Bayesian online changepoint detection. Stat. Optim. Inf. Comput. 1050, 19 (2007)
Aminikhanghahi, S., Cook, D.J.: A survey of methods for time series change point detection. Knowl. Inf. Syst. 51(2), 339–367 (2017)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 3rd International Conference on Learning Representations, ICLR 2015 (2015)
Canizo, M., Triguero, I., Conde, A., Onieva, E.: Multi-head CNN-RNN for multi-time series anomaly detection: an industrial case study. Neurocomputing 363, 246–260 (2019)
Fan, C., et al.: Multi-horizon time series forecasting with temporal attention learning. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2527–2535 (2019)
Fearnhead, P., Rigaill, G.: Changepoint detection in the presence of outliers. J. Am. Stat. Assoc. 114(525), 169–183 (2019)
Hong, T., Pinson, P., Fan, S., Zareipour, H., Troccoli, A., Hyndman, R.J.: Probabilistic energy forecasting: Global energy forecasting competition 2014 and beyond. Int. J. Forecast. 32, 896–913 (2016)
Hori, C., et al.: Attention-based multimodal fusion for video description. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4193–4202 (2017)
Hübner, R., Steinhauser, M., Lehle, C.: A dual-stage two-phase model of selective attention. Psychol. Rev. 117(3), 759 (2010)
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., Soderstrom, T.: Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 387–395 (2018)
Kawahara, Y., Sugiyama, M.: Sequential change-point detection based on direct density-ratio estimation. Stat. Anal. Data Min. 5(2), 114–127 (2012)
Kim, T.Y., Cho, S.B.: Web traffic anomaly detection using C-LSTM neural networks. Exp. Syst. Appl. 106, 66–76 (2018)
Kriegel, H.P., Kroger, P., Schubert, E., Zimek, A.: Interpreting and unifying outlier scores. In: Proceedings of the 2011 SIAM International Conference on Data Mining, pp. 13–24. SIAM (2011)
Liang, Y., Ke, S., Zhang, J., Yi, X., Zheng, Y.: GeoMAN: multi-level attention networks for geo-sensory time series prediction. In: IJCAI, pp. 3428–3434 (2018)
Qin, Y., Song, D., Cheng, H., Cheng, W., Jiang, G., Cottrell, G.W.: A dual-stage attention-based recurrent neural network for time series prediction. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 2627–2633 (2017)
Sadouk, L.: CNN approaches for time series classification. In: Time Series Analysis-Data, Methods, and Applications. IntechOpen (2018)
Salinas, D., Flunkert, V., Gasthaus, J., Januschowski, T.: DeepAR: probabilistic forecasting with autoregressive recurrent networks. Int. J. Forecast. 36, 1181–1191 (2019)
Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Sig. Process. 45(11), 2673–2681 (1997)
Sezer, O.B., Gudelek, M.U., Ozbayoglu, A.M.: Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Appl. Soft Comput. 90, (2020)
Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., Pei, D.: Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2828–2837 (2019)
Xu, H., et al.: Unsupervised anomaly detection via variational auto-encoder for seasonal KPIs in web applications. In: Proceedings of the 2018 World Wide Web Conference, pp. 187–196 (2018)
Zhang, A.Y., Lu, M., Kong, D., Yang, J.: Bayesian time series forecasting with change point and anomaly detection (2018)
Zhang, A., Paisley, J.: Deep Bayesian nonparametric tracking. In: International Conference on Machine Learning, pp. 5833–5841 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Duan, Z., Du, H., Zheng, Y. (2021). Trident: Change Point Detection for Multivariate Time Series via Dual-Level Attention Learning. In: Nguyen, N.T., Chittayasothorn, S., Niyato, D., Trawiński, B. (eds) Intelligent Information and Database Systems. ACIIDS 2021. Lecture Notes in Computer Science(), vol 12672. Springer, Cham. https://doi.org/10.1007/978-3-030-73280-6_63
Download citation
DOI: https://doi.org/10.1007/978-3-030-73280-6_63
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73279-0
Online ISBN: 978-3-030-73280-6
eBook Packages: Computer ScienceComputer Science (R0)