Abstract
Explainable Artificial Intelligence (XAI) aims at introducing transparency and intelligibility into the decision-making process of AI systems. In recent years, most efforts were made to build XAI algorithms that are able to explain black-box models. However, in many cases, including medical and industrial applications, the explanation of a decision may be worth equally or even more than the decision itself. This imposes a question about the quality of explanations. In this work, we aim at investigating how the explanations derived from black-box models combined with XAI algorithms differ from those obtained from inherently interpretable glass-box models. We also aim at answering the question whether there are justified cases to use less accurate glass-box models instead of complex black-box approaches. We perform our study on publicly available 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
Notes
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
Bobek, S., Bałaga, P., Nalepa, G.J.: Towards model-agnostic ensemble explanations. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds.) ICCS 2021. LNCS, vol. 12745, pp. 39–51. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77970-2_4
Bobek, S., Kuk, M., Brzegowski, J., Brzychczy, E., Nalepa, G.J.: KNAC: an approach for enhancing cluster analysis with background knowledge and explanations. CoRR abs/2112.08759 (2021), https://arxiv.org/abs/2112.08759
Bobek, S., Nalepa, G.J.: Introducing uncertainty into explainable AI methods. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds.) ICCS 2021. LNCS, vol. 12747, pp. 444–457. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-77980-1_34
Bobek, S., Nalepa, G.J., Ślażyński, M.: HeaRTDroid - rule engine for mobile and context-aware expert systems. Expert Syst. 36(1), e12328 (2019)
Fung, P.L., et al.: Evaluation of white-box versus black-box machine learning models in estimating ambient black carbon concentration. J. Aerosol Sci. 152, 105694 (2021)
Guidotti, R., Monreale, A., Ruggieri, S., Pedreschi, D., Turini, F., Giannotti, F.: Local rule-based explanations of black box decision systems. ArXiv abs/1805.10820 (2018)
Kaczor, K., Nalepa, G.J.: Critical evaluation of the XTT2 rule representation through comparison with CLIPS. In: KESE@ECAI (2012)
Kuk, M., Bobek, S., Nalepa, G.J.: Explainable clustering with multidimensional bounding boxes, pp. 1–10 (2021). https://doi.org/10.1109/DSAA53316.2021.9564220
Loyola-González, O.: Black-box vs. white-box: understanding their advantages and weaknesses from a practical point of view. IEEE Access 7, 154096–154113 (2019). https://doi.org/10.1109/ACCESS.2019.2949286
Nori, H., Jenkins, S., Koch, P., Caruana, R.: Interpretml: a unified framework for machine learning interpretability (2019)
Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Ribeiro, M.T., Singh, S., Guestrin, C.: Anchors: high-precision model-agnostic explanations. In: AAAI (2018)
Xu, K., et al.: Structured adversarial attack: towards general implementation and better interpretability (2019)
Zhang, X., Wang, N., Shen, H., Ji, S., Luo, X., Wang, T.: Interpretable deep learning under fire (2019)
Acknowledgements
This paper is funded from the XPM (Explainable Predictive Maintenance) project funded by the National Science Center, Poland under CHIST-ERA programme Grant Agreement No. 857925 (NCN UMO-2020/02/Y/ST6/00070)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kuk, M., Bobek, S., Nalepa, G.J. (2022). Comparing Explanations from Glass-Box and Black-Box Machine-Learning Models. In: Groen, D., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2022. ICCS 2022. Lecture Notes in Computer Science, vol 13352. Springer, Cham. https://doi.org/10.1007/978-3-031-08757-8_55
Download citation
DOI: https://doi.org/10.1007/978-3-031-08757-8_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08756-1
Online ISBN: 978-3-031-08757-8
eBook Packages: Computer ScienceComputer Science (R0)