Abstract
Machine Learning (ML) is increasingly used in domains such as cyber-physical systems and enterprise systems. These systems typically operate in non-static environments, prone to unpredictable changes that can adversely impact the accuracy of the ML models, which are usually in the critical path of the systems. Mispredictions of ML components can thus affect other components in the system, and ultimately impact overall system utility in non-trivial ways. From this perspective, self-adaptation techniques appear as a natural solution to reason about how to react to environment changes via adaptation tactics that can potentially improve the quality of ML models (e.g., model retrain), and ultimately maximize system utility. However, adapting ML components is non-trivial, since adaptation tactics have costs and it may not be clear in a given context whether the benefits of ML adaptation outweigh its costs. In this paper, we present a formal probabilistic framework, based on model checking, that incorporates the essential governing factors for reasoning at an architectural level about adapting ML classifiers in a system context. The proposed framework can be used in a self-adaptive system to create adaptation strategies that maximize rewards of a multi-dimensional utility space. Resorting to a running example from the enterprise systems domain, we show how the proposed framework can be employed to determine the gains achievable via ML adaptation and to find the boundary that renders adaptation worthwhile.
Support for this research was provided by Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) through the Carnegie Mellon Portugal Program under Grant SFRH/BD/150643/2020 and via projects with references POCI-01–0247-FEDER-045915, POCI-01–0247-FEDER-045907, and UIDB/50021/2020.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alipourfard, O., et al.: Cherrypick: adaptively unearthing the best cloud configurations for big data analytics. In: Proceedings of NSDI (2017)
Aparício, D., et al.: Arms: Automated rules management system for fraud detection. arXiv preprint. arXiv:2002.06075 (2020)
Bureš, T.: Self-adaptation 2.0. In: Proceedings of SEAMS (2021)
Cámara, J., et al.: Reasoning about sensing uncertainty and its reduction in decision-making for self-adaptation. Sci. Comput. Program. 167, 51–69 (2018)
Cao, Y., Yang, J.: Towards making systems forget with machine unlearning. In: Proceedings of IEEE S & P (2015)
Casimiro, M., et al.: Lynceus: cost-efficient tuning and provisioning of data analytic jobs. In: Proceedings of ICDCS (2020)
Casimiro, M., et al.: Self-adaptation for machine learning based systems. In: Proceedings of SAML. LNCS, Springer (2021)
Cito, J., Dillig, I., Kim, S., Murali, V., Chandra, S.: Explaining mispredictions of machine learning models using rule induction. In: Proceedings of ESEC/FSE (2021)
Cámara, J., Moreno, G., Garlan, D.: Reasoning about human participation in self-adaptive systems. In: Proceedings of SEAMS (2015)
D’Angelo, M., et al.: On learning in collective self-adaptive systems: state of practice and a 3d framework. In: Proceedings of SEAMS (2019)
Diethe, T., et al.: Continual learning in practice. Presented at the NeurIPS 2018 Workshop on Continual Learning (2019)
D’Angelo, M., et al.: Learning to learn in collective adaptive systems: mining design patterns for data-driven reasoning. In: Proceedings of ACSOS-C (2020)
Gheibi, O., Weyns, D., Quin, F.: Applying machine learning in self-adaptive systems: A systematic literature review. arXiv preprint. arXiv:2103.04112 (2021)
Gu, T., et al.: Badnets: evaluating backdooring attacks on deep neural networks. IEEE Access 7, 47230–47244 (2019)
Huang, L., et al.: Adversarial machine learning. In: Proceedings of AISec (2011)
Jamshidi, P., et al.: Transfer learning for improving model predictions in highly configurable software. In: Proceedings of SEAMS (2017)
Kephart, J.O., Chess, D.M.: The vision of autonomic computing. Computer 36(1), 41–50 (2003)
Koh, P.W., et al.: Wilds: A benchmark of in-the-wild distribution shifts. In: Proceedings of ICML. PMLR (2021)
Kwiatkowska, M., Norman, G., Parker, D.: PRISM 4.0: verification of probabilistic real-time systems. In: Gopalakrishnan, G., Qadeer, S. (eds.) CAV 2011. LNCS, vol. 6806, pp. 585–591. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-22110-1_47
Li, J., Hu, M.: Continuous model adaptation using online meta-learning for smart grid application. IEEE Trans. Neural Netw. Learn. Syst. 32(8), 3633–3642 (2021)
Li, N., Adepu, S., Kang, E., Garlan, D.: Explanations for human-on-the-loop: a probabilistic model checking approach. In: Proceedings of SEAMS (2020)
Li, N., Cámara, J., Garlan, D., Schmerl, B.: Reasoning about when to provide explanation for human-in-the-loop self-adaptive systems. In: Proceedings of ACSOS (2020)
Li, N., Cámara, J., Garlan, D., Schmerl, B., Jin, Z.: Hey! preparing humans to do tasks in self-adaptive systems. In: Proceedings of SEAMS (2021)
Liu, B.: Learning on the job: online lifelong and continual learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34 (2020)
Moreno, G.A., et al.: Proactive self-adaptation under uncertainty: a probabilistic model checking approach. In: Proceedings of ESEC/FSE (2015)
Moreno, G.A., et al.: Uncertainty reduction in self-adaptive systems. In: Proceedings of SEAMS (2018)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE TKDE 22(10), 1345–1359 (2009)
Pinto, F., et al.: Automatic model monitoring for data streams. arXiv preprint. arXiv:1908.04240 (2019)
Quionero-Candela, J., et al.: Dataset Shift in Machine Learning. The MIT Press, Cambridge (2009)
Silver, D.L., Yang, Q., Li, L.: Lifelong machine learning systems: beyond learning algorithms. In: 2013 AAAI spring symposium series (2013)
Varshney, K.R., Alemzadeh, H.: On the safety of machine learning: cyber-physical systems, decision sciences, and data products. Big Data 5(3), 246–255 (2017)
Wu, Y., Dobriban, E., Davidson, S.: DeltaGrad: rapid retraining of machine learning models. In: Proceedings of ICML (2020)
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
Casimiro, M., Garlan, D., Cámara, J., Rodrigues, L., Romano, P. (2022). A Probabilistic Model Checking Approach to Self-adapting Machine Learning Systems. In: Cerone, A., et al. Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops. SEFM 2021. Lecture Notes in Computer Science, vol 13230. Springer, Cham. https://doi.org/10.1007/978-3-031-12429-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-12429-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12428-0
Online ISBN: 978-3-031-12429-7
eBook Packages: Computer ScienceComputer Science (R0)