Abstract
Deep neural networks such as Convolutional Neural Networks (CNNs) have been successfully applied to a wide variety of tasks, including time series forecasting. In this paper, we propose a novel approach for online deep CNN selection using saliency maps in the task of time series forecasting. We start with an arbitrarily set of different CNN forecasters with various architectures. Then, we outline a gradient-based technique for generating saliency maps with a coherent design to make it able to specialize the CNN forecasters across different regions in the input time series using a performance-based ranking. In this framework, the selection of the adequate model is performed in an online fashion and the computation of saliency maps responsible for the model selection is achieved adaptively following drift detection in the time series. In addition, the saliency maps can be exploited to provide suitable explanations for the reason behind selecting a specific model at a certain time interval or instant. An extensive empirical study on various real-world datasets demonstrates that our method achieves excellent or on par results in comparison to the state-of-the-art approaches as well as several baselines.
This work is supported by the Deutsche Forschungsgemeinschaft (DFG) within the Collaborative Research Center SFB 876 and the Federal Ministry of Education and Research of Germany as part of the competence center for machine learning ML2R (01–S18038A).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. arXiv preprint arXiv:1810.03292 (2018)
Argiento, R., Guglielmi, A., Pievatolo, A.: Bayesian density estimation and model selection using nonparametric hierarchical mixtures. Comput. Stat. Data Anal. 54(4), 816–832 (2010)
Assaf, R., Schumann, A.: Explainable deep neural networks for multivariate time series predictions. In: IJCAI, pp. 6488–6490 (2019)
Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, vol. 10, pp. 359–370 (1994)
Binkowski, M., Marti, G., Donnat, P.: Autoregressive convolutional neural networks for asynchronous time series. In: International Conference on Machine Learning, pp. 580–589. PMLR (2018)
Birgé, L., Massart, P.: Gaussian model selection. J. Eur. Math. Soc. 3(3), 203–268 (2001)
Borovykh, A., Bohte, S., Oosterlee, C.W.: Conditional time series forecasting with convolutional neural networks. arXiv preprint arXiv:1703.04691 (2017)
Cerqueira, V., Torgo, L., Pinto, F., Soares, C.: Arbitrated ensemble for time series forecasting. In: Ceci, M., Hollmén, J., Todorovski, L., Vens, C., Džeroski, S. (eds.) ECML PKDD 2017. LNCS (LNAI), vol. 10535, pp. 478–494. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-71246-8_29
Cerqueira, V., Torgo, L., Pinto, F., Soares, C.: Arbitrage of forecasting experts. Mach. Learn. 108(6), 913–944 (2018). https://doi.org/10.1007/s10994-018-05774-y
Demertzis, K., Iliadis, L., Anezakis, V.D.: A deep spiking machine-hearing system for the case of invasive fish species. In: INISTA, pp. 23–28 (2017)
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller, P.-A.: Deep learning for time series classification: a review. Data Min. Knowl. Disc. 33(4), 917–963 (2019). https://doi.org/10.1007/s10618-019-00619-1
Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM comput. Surv. (CSUR) 46(4), 1–37 (2014)
Gamboa, J.C.B.: Deep learning for time-series analysis. arXiv preprint arXiv:1701.01887 (2017)
Gers, F.A., Eck, D., Schmidhuber, J.: Applying LSTM to time series predictable through time-window approaches. In: Tagliaferri, R., Marinaro, M. (eds.) Neural Nets. Perspectives in Neural Computing, pp. 193–200. Springer, London (2002). https://doi.org/10.1007/978-1-4471-0219-9_20
Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT Press, Cambridge (2016)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. In: Fisher, N.I., Sen, P.K. (eds.) The Collected Works of Wassily Hoeffding, pp. 409–426. Springer, New York (1994). https://doi.org/10.1007/978-1-4612-0865-5_26
Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79–87 (1991)
Jain, G., Mallick, B.: A study of time series models ARIMA and ETS. Available at SSRN 2898968 (2017)
Kim, T.Y., Cho, S.B.: Predicting residential energy consumption using CNN-LSTM neural networks. Energy 182, 72–81 (2019)
Livieris, I.E., Pintelas, E., Pintelas, P.: A CNN-LSTM model for gold price time-series forecasting. Neural Comput. Appl. 32(23), 17351–17360 (2020)
Mittelman, R.: Time-series modeling with undecimated fully convolutional neural networks. arXiv preprint arXiv:1508.00317 (2015)
Priebe, F.: Dynamic model selection for automated machine learning in time series (2019)
Rivals, I., Personnaz, L.: On cross validation for model selection. Neural Comput. 11(4), 863–870 (1999)
Romeu, P., Zamora-Martínez, F., Botella-Rocamora, P., Pardo, J.: Time-series forecasting of indoor temperature using pre-trained deep neural networks. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 451–458. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40728-4_57
Saadallah, A., Moreira-Matias, L., Sousa, R., Khiari, J., Jenelius, E., Gama, J.: Bright-drift-aware demand predictions for taxi networks. IEEE Trans. Knowl. Data Eng. 32(2), 234–245 (2020)
Saadallah, A., Priebe, F., Morik, K.: A drift-based dynamic ensemble members selection using clustering for time series forecasting (2019)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV, pp. 618–626 (2017)
Taieb, S.B., Bontempi, G., Atiya, A.F., Sorjamaa, A.: A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition. Expert Syst. Appl. 39(8), 7067–7083 (2012)
Utgoff, P.E., Stracuzzi, D.J.: Many-layered learning. Neural Comput. 14(10), 2497–2529 (2002)
Wolpert, D.H.: Stacked generalization. Neural Netw. 5(2), 241–259 (1992)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921–2929 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Saadallah, A., Jakobs, M., Morik, K. (2021). Explainable Online Deep Neural Network Selection Using Adaptive Saliency Maps for Time Series Forecasting. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds) Machine Learning and Knowledge Discovery in Databases. Research Track. ECML PKDD 2021. Lecture Notes in Computer Science(), vol 12975. Springer, Cham. https://doi.org/10.1007/978-3-030-86486-6_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-86486-6_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86485-9
Online ISBN: 978-3-030-86486-6
eBook Packages: Computer ScienceComputer Science (R0)