Abstract
Post-hoc explanation techniques such as the well-established partial dependence plot (PDP), which investigates feature dependencies, are used in explainable artificial intelligence (XAI) to understand black-box machine learning models. While many real-world applications require dynamic models that constantly adapt over time and react to changes in the underlying distribution, XAI, so far, has primarily considered static learning environments, where models are trained in a batch mode and remain unchanged. We thus propose a novel model-agnostic XAI framework called incremental PDP (iPDP) that extends on the PDP to extract time-dependent feature effects in non-stationary learning environments. We formally analyze iPDP and show that it approximates a time-dependent variant of the PDP that properly reacts to real and virtual concept drift. The time-sensitivity of iPDP is controlled by a single smoothing parameter, which directly corresponds to the variance and the approximation error of iPDP in a static learning environment. We illustrate the efficacy of iPDP by showcasing an example application for drift detection and conducting multiple experiments on real-world and synthetic data sets and streams.
M. Muschalik and F. Fumagalli—denotes equal contribution.
We gratefully acknowledge funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation): TRR 318/1 2021 - 438445824.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
iPDP is part of the iXAI framework at https://github.com/mmschlk/iXAI.
- 2.
The debiasing factor ensures that for a constant sequence the exponential moving average remains constant and will be theoretically justified in Sect. 3.3.
- 3.
All experiments are based on sklearn, pytorch and the river online learning framework. All datasets are publicly available and described in the supplement C.1. The code to reproduce the experiments can be found at https://github.com/mmschlk/iPDP-On-Partial-Dependence-Plots-in-Dynamic-Modeling-Scenarios.
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018). https://doi.org/10.1109/ACCESS.2018.2870052
Agrawal, R., Imielinski, T., Swami, A.: Database mining: a performance perspective. IEEE Trans. Knowl. Data Eng. 5(6), 914–925 (1993). https://doi.org/10.1109/69.250074
Apley, D.W., Zhu, J.: Visualizing the effects of predictor variables in black box supervised learning models. J. R. Stat. Soc. Ser. B Stat Methodol. 82(4), 1059–1086 (2020). https://doi.org/10.1111/rssb.12377
Ben-Haim, Y., Tom-Tov, E.: A streaming parallel decision tree algorithm. J. Mach. Learn. Res. 11, 849–872 (2010). https://doi.org/10.5555/1756006.1756034
Berk, R.A., Bleich, J.: Statistical procedures for forecasting criminal behavior: a comparative assessment. Criminol. Public Policy 12, 513 (2013)
Bifet, A., Gavaldà, R.: Learning from time-changing data with adaptive windowing. In: Proceedings of the Seventh SIAM International Conference on Data Mining (SIAM 2007), pp. 443–448 (2007). https://doi.org/10.1137/1.9781611972771.42
Bifet, A., Gavaldà, R.: Adaptive learning from evolving data streams. In: Adams, N.M., Robardet, C., Siebes, A., Boulicaut, J.-F. (eds.) IDA 2009. LNCS, vol. 5772, pp. 249–260. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-03915-7_22
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Britton, M.: VINE: visualizing statistical interactions in black box models. CoRR abs/1904.00561 (2019). http://arxiv.org/abs/1904.00561
Cassidy, A.P., Deviney, F.A.: Calculating feature importance in data streams with concept drift using online random forest. In: 2014 IEEE International Conference on Big Data (Big Data 2014), pp. 23–28 (2014). https://doi.org/10.1109/BigData.2014.7004352
Clements, J.M., Xu, D., Yousefi, N., Efimov, D.: Sequential deep learning for credit risk monitoring with tabular financial data. CoRR abs/2012.15330 (2020). https://arxiv.org/abs/2012.15330
Covert, I., Lundberg, S.M., Lee, S.: Understanding global feature contributions with additive importance measures. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (NeurIPS 2020) (2020)
Davari, N., Veloso, B., Ribeiro, R.P., Pereira, P.M., Gama, J.: Predictive maintenance based on anomaly detection using deep learning for air production unit in the railway industry. In: 8th IEEE International Conference on Data Science and Advanced Analytics (DSAA 2021), pp. 1–10. IEEE (2021). https://doi.org/10.1109/DSAA53316.2021.9564181
Domingos, P., Hulten, G.: Mining high-speed data streams. In: Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD 2000), pp. 71–80 (2000). https://doi.org/10.1145/347090.347107
Duckworth, C., et al.: Using explainable machine learning to characterize data drift and detect emergent health risks for emergency department admissions during COVID-19. Sci. Rep. 11(1), 23017 (2021). https://doi.org/10.1038/s41598-021-02481-y
Elith, J., Leathwick, J.R., Hastie, T.: A working guide to boosted regression trees. J. Anim. Ecol. 77(4), 802–813 (2008). https://doi.org/10.1111/j.1365-2656.2008.01390.x
Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001). http://www.jstor.org/stable/2699986
Frye, C., Mijolla, D.D., Begley, T., Cowton, L., Stanley, M., Feige, I.: Shapley explainability on the data manifold. In: International Conference on Learning Representations (ICLR 2021) (2021). https://openreview.net/forum?id=OPyWRrcjVQw
Fumagalli, F., Muschalik, M., Hüllermeier, E., Hammer, B.: Incremental permutation feature importance (iPFI): towards online explanations on data streams. CoRR abs/2209.01939 (2022). https://doi.org/10.48550/arXiv.2209.01939
Gama, J., Zliobaite, I., Bifet, A., Pechenizkiy, M., Bouchachia, A.: A survey on concept drift adaptation. ACM Comput. Surv. 46(4), 44:1–44:37 (2014). https://doi.org/10.1145/2523813
García-Martín, E., Rodrigues, C.F., Riley, G., Grahn, H.: Estimation of energy consumption in machine learning. J. Parallel Distrib. Comput. 134, 75–88 (2019). https://doi.org/10.1016/j.jpdc.2019.07.007
Goldstein, A., Kapelner, A., Bleich, J., Pitkin, E.: Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J. Comput. Graph. Stat. 24(1), 44–65 (2015). https://doi.org/10.1080/10618600.2014.907095
Gomes, H.M., et al.: Adaptive random forests for evolving data stream classification. Mach. Learn. 106(9), 1469–1495 (2017)
Gomes, H.M., Mello, R.F.D., Pfahringer, B., Bifet, A.: Feature scoring using tree-based ensembles for evolving data streams. In: 2019 IEEE International Conference on Big Data (Big Data 2019), pp. 761–769 (2019)
Greenwell, B.M., Boehmke, B.C., McCarthy, A.J.: A simple and effective model-based variable importance measure. CoRR abs/1805.04755 (2018). http://arxiv.org/abs/1805.04755
Grömping, U.: Model-agnostic effects plots for interpreting machine learning models. In: Reports in Mathematics, Physics and Chemistry: Department II. Beuth University of Applied Sciences Berlin (2020). http://www1.beuth-hochschule.de/FB_II/reports/
Harries, M.: SPLICE-2 comparative evaluation: electricity pricing. Technical report, The University of South Wales (1999)
Haug, J., Braun, A., Zürn, S., Kasneci, G.: Change detection for local explainability in evolving data streams. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKIM 2022), pp. 706–716. ACM (2022). https://doi.org/10.1145/3511808.3557257
Herbinger, J., Bischl, B., Casalicchio, G.: REPID: regional effect plots with implicit interaction detection. In: International Conference on Artificial Intelligence and Statistics, (AISTATS 2022). Proceedings of Machine Learning Research, vol. 151, pp. 10209–10233. PMLR (2022). https://proceedings.mlr.press/v151/herbinger22a.html
Hinder, F., Vaquet, V., Brinkrolf, J., Hammer, B.: Model based explanations of concept drift. CoRR abs/2303.09331 (2023). https://doi.org/10.48550/arXiv.2303.09331
Hulten, G., Spencer, L., Domingos, P.: Mining time-changing data streams. In: Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD 2001), pp. 97–106 (2001). https://doi.org/10.1145/502512.502529
Janzing, D., Minorics, L., Blöbaum, P.: Feature relevance quantification in explainable AI: a causal problem. In: International Conference on Artificial Intelligence and Statistics (AISTATS 2020). Proceedings of Machine Learning Research, vol. 108, pp. 2907–2916. PMLR (2020). http://proceedings.mlr.press/v108/janzing20a
Losing, V., Hammer, B., Wersing, H.: Incremental on-line learning: a review and comparison of state of the art algorithms. Neurocomputing 275, 1261–1274 (2018). https://doi.org/10.1016/j.neucom.2017.06.084
Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., Zhang, G.: Learning under concept drift: a review. IEEE Trans. Knowl. Data Eng. 2346–2363 (2018). https://doi.org/10.1109/TKDE.2018.2876857
Lundberg, S.M., Erion, G.G., Lee, S.: Consistent individualized feature attribution for tree ensembles. CoRR abs/1802.03888 (2018). http://arxiv.org/abs/1802.03888
Molnar, C.: Interpretable Machine Learning, 2 edn. (2022). Lulu.com, https://christophm.github.io/interpretable-ml-book
Molnar, C., König, G., Bischl, B., Casalicchio, G.: Model-agnostic feature importance and effects with dependent features - a conditional subgroup approach. CoRR abs/2006.04628 (2020). https://arxiv.org/abs/2006.04628
Molnar, C., et al.: General pitfalls of model-agnostic interpretation methods for machine learning models. In: Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, K.R., Samek, W. (eds.) xxAI 2020. LNCS, vol. 13200, pp. 39–68. Springer, Cham (2020). https://doi.org/10.1007/978-3-031-04083-2_4
Moosbauer, J., Herbinger, J., Casalicchio, G., Lindauer, M., Bischl, B.: Explaining hyperparameter optimization via partial dependence plots. In: Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021 (NeurIPS 2021), pp. 2280–2291 (2021). https://proceedings.neurips.cc/paper/2021/hash/12ced2db6f0193dda91ba86224ea1cd8-Abstract.html
Muschalik, M., Fumagalli, F., Hammer, B., Hüllermeier, E.: Agnostic explanation of model change based on feature importance. Künstliche Intell. 36(3), 211–224 (2022). https://doi.org/10.1007/s13218-022-00766-6
Muschalik, M., Fumagalli, F., Hammer, B., Hüllermeier, E.: iSAGE: an incremental version of SAGE for online explanation on data streams. CoRR abs/2303.01181 (2023). https://doi.org/10.48550/arXiv.2303.01181
Parisi, G.I., Kemker, R., Part, J.L., Kanan, C., Wermter, S.: Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54–71 (2019). https://doi.org/10.1016/j.neunet.2019.01.012
Rouleau, J., Gosselin, L.: Impacts of the COVID-19 lockdown on energy consumption in a Canadian social housing building. Appl. Energy 287, 116565 (2021). https://doi.org/10.1016/j.apenergy.2021.116565
Susnjak, T., Maddigan, P.: Forecasting patient flows with pandemic induced concept drift using explainable machine learning. EPJ Data Sci. 12(1), 11 (2023). https://doi.org/10.1140/epjds/s13688-023-00387-5
Ta, V.D., Liu, C.M., Nkabinde, G.W.: Big data stream computing in healthcare real-time analytics. In: Proceddings of International Conference on Cloud Computing and Big Data Analysis (ICCCBDA 2016), pp. 37–42 (2016). https://doi.org/10.1109/ICCCBDA.2016.7529531
Zhao, X., Yang, H., Yao, Y., Qi, H., Guo, M., Su, Y.: Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots. Phys. A 598, 127343 (2022). https://doi.org/10.1016/j.physa.2022.127343
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
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Muschalik, M., Fumagalli, F., Jagtani, R., Hammer, B., Hüllermeier, E. (2023). iPDP: On Partial Dependence Plots in Dynamic Modeling Scenarios. In: Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science, vol 1901. Springer, Cham. https://doi.org/10.1007/978-3-031-44064-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-44064-9_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44063-2
Online ISBN: 978-3-031-44064-9
eBook Packages: Computer ScienceComputer Science (R0)