Abstract
In this paper we focus on explanation methods for time series classification. In particular, we aim to quantitatively assess and rank different explanation methods based on their informativeness. In many applications, it is important to understand which parts of the time series are informative for the classification decision. For example, while doing a physio exercise, the patient receives feedback on whether the execution is correct or not (classification), and if not, which parts of the motion are incorrect (explanation), so they can take remedial action. Comparing explanations is a non-trivial task. It is often unclear if the output presented by a given explanation method is at all informative (i.e., relevant for the classification task) and it is also unclear how to compare explanation methods side-by-side. While explaining classifiers for image data has received quite some attention, explanation methods for time series classification are less explored. We propose a model-agnostic approach for quantifying and comparing different saliency-based explanations for time series classification. We extract importance weights for each point in the time series based on learned classifier weights and use these weights to perturb specific parts of the time series and measure the impact on classification accuracy. By this perturbation, we show that explanations that actually highlight discriminative parts of the time series lead to significant changes in classification accuracy. This allows us to objectively quantify and rank different explanations. We provide a quantitative and qualitative analysis for a few well known UCR datasets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Retrieved from: https://github.com/lnthach/Mr-SEQL/tree/master/data/CMJ.
References
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., Kim, B.: Sanity checks for saliency maps. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, NIPS 2018, pp. 9525–9536. Curran Associates Inc., Red Hook (2018)
Apley, D.W., Zhu, J.: Visualizing the effects of predictor variables in black box supervised learning models (2016)
Avci, A., Bosch, S., Marin-Perianu, M., Marin-Perianu, R., Havinga, P.: Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: a survey, pp. 167–176 (01 2010)
Bagnall, A., Lines, J., Bostrom, A., Large, J., Keogh, E.: The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 1–55 (2016). https://doi.org/10.1007/s10618-016-0483-9
Bostrom, A., Bagnall, A.: Binary Shapelet transform for multiclass time series classification. In: Madria, S., Hara, T. (eds.) DaWaK 2015. LNCS, vol. 9263, pp. 257–269. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-22729-0_20
Bostrom, N., Yudkowsky, E.: The ethics of artificial intelligence (2011)
Dau, H.A., et al.: Hexagon-ML: The UCR time series classification archive, October 2018. https://www.cs.ucr.edu/~eamonn/time_series_data_2018/
Dempster, A., Petitjean, F., Webb, G.I.: Rocket: exceptionally fast and accurate time series classification using random convolutional kernels (2019)
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning (2017)
Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously (2018)
Grabocka, J., Schilling, N., Wistuba, M., Schmidt-Thieme, L.: Learning time-series Shapelets. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014, pp. 392–401. ACM, New York (2014). https://doi.org/10.1145/2623330.2623613
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Ifrim, G., Wiuf, C.: Bounded coordinate-descent for biological sequence classification in high dimensional predictor space. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2011, pp. 708–716. Association for Computing Machinery, New York (2011). https://doi.org/10.1145/2020408.2020519
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller,P.A.: Accurate and interpretable evaluation of surgical skills from kinematic datausing fully convolutional neural networks. Int. J. Comput. Assist. Radiol. Surg. 14(9), 1611–1617 (2019).https://doi.org/10.1007/s11548-019-02039-4
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., Muller,P.A.: Deep learning for time series classification: a review. Data Min. Knowl Disc. (2019). https://doi.org/10.1007/s10618-019-00619-1
Keogh, E., Ratanamahatana, C.A.: Exact indexing of dynamic time warping. Knowl. Inf. Syst. 7(3), 358–386 (2005). https://doi.org/10.1007/s10115-004-0154-9
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012). http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
Le Nguyen, T., Gsponer, S., Ilie, I., O’Reilly, M., Ifrim, G.: Interpretable time series classification using linear models and multi-resolution multi-domain symbolic representations. Data Min. Knowl. Disc. 33(4), 1183–1222 (2019). https://doi.org/10.1007/s10618-019-00633-3
Lin, J., Keogh, E., Wei, L., Lonardi, S.: Experiencing sax: a novel symbolic representation of time series. Data Min. Knowl. Disc. 15(2), 107–144 (2007). https://doi.org/10.1007/s10618-007-0064-z
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774. Curran Associates, Inc. (2017). http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf
Nguyen, T.L., Gsponer, S., Ifrim, G.: Time series classification by sequence learning in all-subsequence space. In: IEEE 33rd International Conference on Data Engineering (ICDE), pp. 947–958, April 2017. https://doi.org/10.1109/ICDE.2017.142
Petitjean, F., Forestier, G., Webb, G.I., Nicholson, A.E., Chen, Y., Keogh, E.: Dynamic time warping averaging of time series allows faster and more accurate classification. In: IEEE International Conference on Data Mining, pp. 470–479 (2014)
Ramgopal, S., et al.: Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy. Epilepsy Behav. E&B 37C, 291–307 (2014). https://doi.org/10.1016/j.yebeh.2014.06.023
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?: explaining the predictions of any classifier. CoRR abs/1602.04938 (2016). http://arxiv.org/abs/1602.04938
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: High-precision model-agnostic explanations. In: AAAI (2018)
Schäfer, P.: The boss is concerned with time series classification in the presence of noise. Data Min. Knowl. Discov. 29(6), 1505–1530 (2015)
Schäfer, P., Leser, U.: Fast and accurate time series classification with weasel. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, pp. 637–646. ACM, New York (2017). https://doi.org/10.1145/3132847.3132980
Selvaraju, R.R., Das, A., Vedantam, R., Cogswell, M., Parikh, D., Batra, D.: Grad-CAM: why did you say that? visual explanations from deep networks via gradient-based localization. CoRR abs/1610.02391 (2016). http://arxiv.org/abs/1610.02391
Senin, P., Malinchik, S.: SAX-VSM: interpretable time series classification using sax and vector space model. In: IEEE 13th International Conference on Data Mining (ICDM), pp. 1175–1180, December 2013. https://doi.org/10.1109/ICDM.2013.52
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. Preprint, December 2013
Smilkov, D., Thorat, N., Kim, B., Viégas, F.B., Wattenberg, M.: Smoothgrad: removing noise by adding noise. CoRR abs/1706.03825 (2017), http://arxiv.org/abs/1706.03825
Springenberg, J., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: ICLR (workshop track) (2015). http://lmb.informatik.uni-freiburg.de/Publications/2015/DB15a
Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–9 (2015)
Wachter, S., Mittelstadt, B.D., Russell, C.: Counterfactual explanations without opening the black box: automated decisions and the GDPR. CoRR abs/1711.00399 (2017). http://arxiv.org/abs/1711.00399
Wang, Z., Yan, W., Oates, T.: Time series classification from scratch with deep neural networks: a strong baseline. In: International Joint Conference on Neural Networks (IJCNN), pp. 1578–1585, May 2017. https://doi.org/10.1109/IJCNN.2017.7966039
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR (2016)
Acknowledgments
This work was funded by Science Foundation Ireland through the SFI Centre for Research Training in Machine Learning (18/CRT/6183), the Insight Centre for Data Analytics (12/RC/2289_P2) and the VistaMilk SFI Research Centre (SFI/16/RC/3835).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Nguyen, T.T., Le Nguyen, T., Ifrim, G. (2020). A Model-Agnostic Approach to Quantifying the Informativeness of Explanation Methods for Time Series Classification. In: Lemaire, V., Malinowski, S., Bagnall, A., Guyet, T., Tavenard, R., Ifrim, G. (eds) Advanced Analytics and Learning on Temporal Data. AALTD 2020. Lecture Notes in Computer Science(), vol 12588. Springer, Cham. https://doi.org/10.1007/978-3-030-65742-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-65742-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-65741-3
Online ISBN: 978-3-030-65742-0
eBook Packages: Computer ScienceComputer Science (R0)