Abstract
Anomaly detection, though, is a common and intensively studied data mining problem in many applications, its online (incremental) algorithm is yet to be proposed and investigated, especially with respect to the use of tensor technique. As online (incremental) learning is becoming increasingly more important, we propose a novel online anomaly detection algorithm using incremental tensor decomposition. The online approach keeps updating the model while new data arrive, in contrast to the conventional approach that requests all data to re-build the model. In addition, the online algorithm can not only track the trend in time evolving data, but also requests less memory since only the new data is necessary for model updating. The experimental results show that the presented algorithm has sound discriminative power that is essential for anomaly detection. In addition, the number of anomalies can be flexibly adjusted by the parameters in the algorithm, which is necessary in some real-world scenarios. The effects of these parameters are also consistent using two experimental datasets.
M. Gao, Y. Zong and R. Li—Both authors contributed equally to this study.
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
Notes
- 1.
Tensor decomposition and tensor factorization (TF) are often used interchangeably.
- 2.
We use \(A,\;B,\;C\) on the superscripts to represent the respective modes in the tensor \(\mathcal {T}\).
- 3.
“\(\odot \)” denotes the Khatri–Rao product, “\(\circ \)” denotes the vector outer product, “\(*\)” denotes the Hadamard product that is the elementwise matrix product, the superscript “\(^+\)” denotes pseudo inverse.
References
Brett, W.B., Tamara, G.K, et al.: MATLAB tensor toolbox version 2.6, February 2015
Bifet, A., Holmes, G., Kirkby, R., Pfahringer, B.: Moa: massive online analysis. J. Mach. Learn. Res. 11, 1601–1604 (2010)
Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. 41(3), 15:1–15:58 (2009)
Cai, D., Hou, D., Qi, Y., Yan, J., Lu, Y.: A distributed rule engine for streaming big data. In: Meng, X., Li, R., Wang, K., Niu, B., Wang, X., Zhao, G. (eds.) WISA 2018. LNCS, vol. 11242, pp. 123–130. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-02934-0_12
Domingos, P., Hulten, G.: Mining high-speed data streams. In: Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2000, pp. 71–80. ACM, New York, NY, USA (2000)
Feng, J., Zhang, C., Hao, P.: Online learning with self-organizing maps for anomaly detection in crowd scenes. In: 2010 20th International Conference on Pattern Recognition, pp. 3599–3602 (2010)
Gujral, E., Pasricha, R., Papalexakis, E.: Sambaten: Sampling-based batch incremental tensor decomposition, pp. 387–395 (2018)
Hitchcock, F.L.: The expression of a tensor or a polyadic as a sum of products. J. Math. Phys. 6(1), 164–189 (1927)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Laxhammar, R., Falkman, G.: Online learning and sequential anomaly detection in trajectories. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1158–1173 (2014)
Lev-ari, H.: Efficient solution of linear matrix equations with application to multistatic antenna array processing. Commun. Inf. Syst. 5, 123–130 (2005)
Li, J., Han, G., Wen, J., Gao, X.: Robust tensor subspace learning for anomaly detection. Int. J. Mach. Learn. Cybern. 2(2), 89–98 (2011)
Nickel, M., Tresp, V.: Tensor factorization for multi-relational learning. In: Blockeel, H., Kersting, K., Nijssen, S., Železný, F. (eds.) ECML PKDD 2013. LNCS (LNAI), vol. 8190, pp. 617–621. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40994-3_40
Papalexakis, E.E., Faloutsos, C., Sidiropoulos, N.D.: Tensors for data mining and data fusion: models, applications, and scalable algorithms. ACM Trans. Intell. Syst. Technol. 8(2), 16:1–16:44 (2016)
Sun, J., Tao, D., Faloutsos, C.: Beyond streams and graphs: Dynamic tensor analysis. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2006, pp. 374–383. ACM, New York, NY, USA (2006)
Sun, J., Tao, D., Papadimitriou, S., Yu, P.S., Faloutsos, C.: Incremental tensor analysis: theory and applications. ACM Trans. Knowl. Discov. Data 2(3), 11:1–11:37 (2008)
Tucker, L.R.: Some mathematical notes on three-mode factor analysis. JPsychometrika 31(3), 279–311 (1966)
Vespe, M., Visentini, I., Bryan, K., Braca, P.: Unsupervised learning of maritime traffic patterns for anomaly detection. In: 9th IET Data Fusion & Target Tracking Conference (DF & TT 2012): Algorithms & Applications, p. 14. IET (2012)
Li, Y., Wen, Y., Yuan, X.: Online aggregation: a review. In: Meng, X., Li, R., Wang, K., Niu, B., Wang, X., Zhao, G. (eds.) WISA 2018. LNCS, vol. 11242, pp. 103–114. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-02934-0_10
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gao, M. et al. (2019). Online Anomaly Detection via Incremental Tensor Decomposition. In: Ni, W., Wang, X., Song, W., Li, Y. (eds) Web Information Systems and Applications. WISA 2019. Lecture Notes in Computer Science(), vol 11817. Springer, Cham. https://doi.org/10.1007/978-3-030-30952-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-30952-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30951-0
Online ISBN: 978-3-030-30952-7
eBook Packages: Computer ScienceComputer Science (R0)
