Abstract
Regression models are commonly used to model the associations between a set of features and an observed outcome, for purposes such as prediction, finding associations, and determining causal relationships. However, interpreting the outputs of these models can be challenging, especially in complex models with many features and nonlinear interactions. Current methods for explaining regression models include simplification, visual, counterfactual, example-based, and attribute-based approaches. Furthermore, these methods often provide only a global or local explanation. In this paper, we propose a hybrid multilevel explanation (Hybrid Multilevel Explanation - HuMiE) method that enhances example-based explanations for regression models. In addition to a set of instances capable of representing the learned model, the HuMiE method provides a complete understanding of why an output is obtained by explaining the reasons in terms of attribute importance and expected values in similar instances. This approach also provides intermediate explanations between global and local explanations by grouping semantically similar instances during the explanation process. The proposed method offers a new possibility of understanding complex models and proved to be able to find examples statistically equal to or better than the main competing methods and to provide a coherent explanation with the context of the explained model.
This work was supported by FAPEMIG (through the grant no. CEX-PPM-00098-17), MPMG (through the project Analytical Capabilities), CNPq (through the grant no. 310833/2019-1), CAPES, MCTIC/RNP (through the grant no. 51119) and IFMG - Campus Sabará.
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
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)
Bien, J., Tibshirani, R.: Prototype selection for interpretable classification. Ann. Appl. Stat. 5(4), 2403–2424 (2011)
Carvalho, D.V., Pereira, E.M., Cardoso, J.S.: Machine learning interpretability: A survey on methods and metrics. Electronics 8(8), 832 (2019)
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Filho, R.M.: Explaining Regression Models Predictions. Ph.D. thesis, Universidade Federal de Minas Gerais (2023)
Filho, R.M., Lacerda, A., Pappa, G.L.: Explaining symbolic regression predictions. In: 2020 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8 (2020)
Filho, R.M., Lacerda, A.M., Pappa, G.L.: Explainable regression via prototypes. ACM Trans. Evol. Learn. Optim. 2(4) (2023)
Grari, V., Lamprier, S., Detyniecki, M.: Adversarial learning for counterfactual fairness. Mach. Learn. 11, 1–23 (2022)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. 51(5), 9:31-93:42 (2018)
Gurumoorthy, K.S., Dhurandhar, A., Cecchi, G.A., Aggarwal, C.C.: Efficient data representation by selecting prototypes with importance weights. In: ICDM 2019 (2019)
Kim, B., Khanna, R., Koyejo, O.O.: Examples are not enough, learn to criticize! criticism for interpretability. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)
Letzgus, S., Wagner, P., Lederer, J., Samek, W., Muller, K.R., Montavon, G.: Toward explainable artificial intelligence for regression models: a methodological perspective. IEEE Sig. Process. Mag. 39(4), 40–58 (2022)
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)
Melis, D.A., Jaakkola, T.: Towards robust interpretability with self-explaining neural networks. In: NeurIPS 2018, pp. 7775–7784 (2018)
Ming, Y., Xu, P., Qu, H., Ren, L.: Interpretable and steerable sequence learning via prototypes. In: KDD 2019, pp. 903–913 (2019)
Molnar, C.: Interpretable Machine Learning, 2nd edn. Lulu.com (2022). https://christophm.github.io/interpretable-ml-book
Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* 2020, pp. 607–617. Association for Computing Machinery, New York, NY, USA (2020)
Plumb, G., Al-Shedivat, M., Xing, E.P., Talwalkar, A.: Regularizing black-box models for improved interpretability. CoRR (2019)
Ramamurthy, K.N., Vinzamuri, B., Zhang, Y., Dhurandhar, A.: Model agnostic multilevel explanations. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020. Advances in Neural Information Processing Systems 33, 6–12 December 2020, Virtual (2020)
Ribeiro, M.T., Singh, S., Guestrin, C.: “why should i trust you?”: explaining the predictions of any classifier. In: Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2016, pp. 1135–1144. ACM, New York, NY, USA (2016)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should i trust you?” Explaining the predictions of any classifier. In: KDD 2016, pp. 1135–1144 (2016)
Schwab, P., Karlen, W.: CXPlain: causal explanations for model interpretation under uncertainty. In: NeurIPS 2019, pp. 10220–10230 (2019)
Zhao, Q., Hastie, T.: Causal interpretations of black-box models. J. Bus. Econ. Stat. 39(1), 272–281 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Filho, R.M., Pappa, G.L. (2023). Hybrid Multilevel Explanation: A New Approach for Explaining Regression Models. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14195. Springer, Cham. https://doi.org/10.1007/978-3-031-45368-7_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-45368-7_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45367-0
Online ISBN: 978-3-031-45368-7
eBook Packages: Computer ScienceComputer Science (R0)