Abstract
Adapting to data distribution shifts after training remains a significant challenge within the realm of Artificial Intelligence. This paper presents a refined approach, superior to Automated Hyper Parameter Tuning methods, that effectively detects and learns from such shifts to improve the efficacy of prediction models. By integrating Explainable AI (XAI) techniques into adaptive learning with SHAP clustering, we generate interpretable model explanations and use these insights for adaptive refinement. Our three-stage process: (1) SHAP value generation for the model explanation, (2) clustering these values for pattern identification, and (3) model refinement based on the derived SHAP cluster characteristics, mitigates overfitting and ensures robust data shift handling. We evaluate our method on a comprehensive dataset comprising energy consumption records of buildings, as well as two additional datasets, to assess the transferability of our approach to other domains, regression, and classification problems. Our experiments highlight that our method not only improves predictive performance in both task types but also delivers interpretable model explanations, offering significant value in dealing with the challenges of data distribution shifts in AI.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Clustering – scikit-learn 1.2.1 documentation. https://scikit-learn.org/stable/modules/clustering.html#dbscan. Accessed 28 Feb 2023
Amiri, S.S., Mottahedi, S., Lee, E.R., Hoque, S.: Peeking inside the black-box: explainable machine learning applied to household transportation energy consumption. Comput. Environ. Urban Syst. 88, 101647 (2021)
Bigdeli, E., Mohammadi, M., Raahemi, B., Matwin, S.: A fast and noise resilient cluster-based anomaly detection. Pattern Anal. Appl. 20, 183–199 (2017)
Clement, T., Kemmerzell, N., Abdelaal, M., Amberg, M.: XAIR: a systematic metareview of explainable AI (XAI) aligned to the software development process. Mach. Learn. Knowl. Extr. 5(1), 78–108 (2023)
Dave, R.N.: Characterization and detection of noise in clustering. Pattern Recogn. Lett. 12(11), 657–664 (1991)
Durvasula, N., d’Hauteville, V., Hines, K., Dickerson, J.P.: Characterizing anomalies with explainable classifiers. In: NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications
Gal, Y., Islam, R., Ghahramani, Z.: Deep Bayesian active learning with image data. In: International Conference on Machine Learning, pp. 1183–1192. PMLR (2017)
Gautam, S., Höhne, M.M.C., Hansen, S., Jenssen, R., Kampffmeyer, M.: This looks more like that: enhancing self-explaining models by prototypical relevance propagation. Pattern Recogn. 136, 109172 (2023)
Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. MIT Press, Cambridge (2016)
Hart, S.: Shapley Value. In: In: Eatwell, J., Milgate, M., Newman, P. (eds.) Game Theory. The New Palgrave, pp. 210–216. Palgrave Macmillan, London (1989). https://doi.org/10.1007/978-1-349-20181-5_25
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems vol. 30, pp. 4765–4774. Curran Associates, Inc. (2017)
Nguyen, H.T.T., Cao, H.Q., Nguyen, K.V.T., Pham, N.D.K.: Evaluation of explainable artificial intelligence: shap, lime, and cam. In: Proceedings of the FPT AI Conference, pp. 1–6 (2021)
Nguyen, T.T.H., Truong, V.B., Nguyen, V.T.K., Cao, Q.H., Nguyen, Q.K.: Towards trust of explainable AI in thyroid nodule diagnosis. arXiv preprint arXiv:2303.04731 (2023)
Shen, Z., Shrestha, S., Howard, D., Feng, T., Hun, D., She, B.: Machine learning-assisted prediction of heat fluxes through thermally anisotropic building envelopes. Build. Environ. 234, 110157 (2023)
Shivaswamy, P., Joachims, T.: Coactive learning. J. Artif. Intell. Res. 53, 1–40 (2015)
Shutaywi, M., Kachouie, N.N.: Silhouette analysis for performance evaluation in machine learning with applications to clustering. Entropy 23(6), 759 (2021)
Skillington, K., Crawford, R.H., Warren-Myers, G., Davidson, K.: A review of existing policy for reducing embodied energy and greenhouse gas emissions of buildings. Energy Policy 168, 112920 (2022)
Still, S., Bialek, W.: How many clusters? An information-theoretic perspective. Neural Comput. 16(12), 2483–2506 (2004)
Victoria, A.H., Maragatham, G.: Automatic tuning of hyperparameters using Bayesian optimization. Evol. Syst. 12, 217–223 (2021)
Weber, L., Lapuschkin, S., Binder, A., Samek, W.: Beyond explaining: opportunities and challenges of XAI-based model improvement. Inf. Fusion 92, 154–176 (2023). https://doi.org/10.1016/j.inffus.2022.11.013
Zambrano, J.M., Oberegger, U.F., Salvalai, G.: Towards integrating occupant behaviour modelling in simulation-aided building design: reasons, challenges and solutions. Energy Build. 253, 111498 (2021)
Zunino, A., Bargal, S.A., Morerio, P., Zhang, J., Sclaroff, S., Murino, V.: Excitation dropout: encouraging plasticity in deep neural networks. Int. J. Comput. Vis. 129, 1139–1152 (2021)
Acknowledgments
This work was supported by the Federal Ministry of Education and Research through grant 01IS17045 (Software Campus project).
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
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Clement, T., Nguyen, H.T.T., Kemmerzell, N., Abdelaal, M., Stjelja, D. (2024). Coping with Data Distribution Shifts: XAI-Based Adaptive Learning with SHAP Clustering for Energy Consumption Prediction. In: Liu, T., Webb, G., Yue, L., Wang, D. (eds) AI 2023: Advances in Artificial Intelligence. AI 2023. Lecture Notes in Computer Science(), vol 14472. Springer, Singapore. https://doi.org/10.1007/978-981-99-8391-9_12
Download citation
DOI: https://doi.org/10.1007/978-981-99-8391-9_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8390-2
Online ISBN: 978-981-99-8391-9
eBook Packages: Computer ScienceComputer Science (R0)