Abstract
The importance of extracting constraints from data is emphasized by its potential practical applications in solving real-world problems. While constraints are commonly used for modeling and problem-solving, methods for learning constraints from data are still relatively scarce. Moreover, the complex nature of modeling requires expertise and is susceptible to errors, making constraint acquisition methods valuable for automating this process through learning constraints from examples or behaviours of solutions and non-solutions. This study introduces a novel approach grounded in Deep Neural Networks (DNN) based on Symbolic Regression, where suitable loss functions are used to extract constraints directly from datasets. With this approach, constraints can be directly formulated. Additionally, given the wide range of pre-developed architectures and functionalities of DNNs, potential connections and extensions with other frameworks are foreseeable.
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
Similar content being viewed by others
References
O’Sullivan, B.: Automated modelling and solving in constraint programming. In: Twenty-Fourth AAAI Conference on Artificial Intelligence, vol. 24, no. 1, p. 2010 (2010)
Bessiere, C., et al.: Constraint acquisition via partial queries. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence (IJCAI 2013), Beijing, pp. 475–481 (2013)
Daoudi, A., Mechqrane, Y., Bessiere, C., Lazaar, N., Bouyakhf, E.H.: Constraint acquisition using recommendation queriesff. In: International Joint Conference on Artificial Intelligence (IJCAI), New York, pp. 720–726 (2016)
Beldiceanu, N., Simonis, H.: ModelSeeker: extracting global constraint models from positive examples. In: Bessiere, C., De Raedt, L., Kotthoff, L., Nijssen, S., O’Sullivan, B., Pedreschi, D. (eds.) Data Mining and Constraint Programming. LNCS (LNAI), vol. 10101, pp. 77–95. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50137-6_4
Arcangioli, R., Bessiere, C., Lazaar, N.: Multiple constraint acquisition. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16), New York (2016)
Tsouros, D.C., Stergiou, K.: Efficient multiple constraint acquisition. Constraints 25, 181–225 (2020)
Daoudi, A., Mechqrane, Y., Bessiere, C., Lazaar, N., Bouyakhf, E.H.: Constraint acquisition using recommendation queries. In: International Joint Conference on Artificial Intelligence (IJCAI), pp. 720– 726 (2016)
Bau, D., Zhu, J.-Y., Strobelt, H., Lapedriza, A., Zhou, B., Torralba, A.: PNAS 117(48), 30071–30078 (2020)
Donges, N.: (Updated Matthew Urwin). 4 Disadvantages of Neural Networks. (2023). https://builtin.com/data-science/disadvantages-neural-networks. Accessed 12 Jan 2024
Church, K.W., Chen, Z., Ma, Y.: Emerging trends: a gentle introduction to fine-tuning. Nat. Lang. Eng. 27, 763–778 (2021)
Dash, T., Chitlangia, S., Ahuja, A., Srinivasan, A.: A review of some techniques for inclusion of domain-knowledge into deep neural networks. Sci. Rep. 12, 1040 (2022)
Sun, L., Gao, H., Pan, S., Wang, J.X.: Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data. Comput. Methods Appl. Mech. Eng. 361, 112732 (2020)
He, B., Lu, Q., Yang, Q., Luo, J., Wang, Z.: Taylor genetic programming for symbolic regression. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 946–954 (2022)
La Cava, W., et al.: Contemporary symbolic regression methods and their relative performance. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol. 1 (2021)
Wang, Q., Ma, Y., Zhao, K., Tian, Y.: A comprehensive survey of loss functions in machine learning. Annal. Data Sci. 9, 187–212 (2022)
Schmidt, M., Lipson, H.: Distilling free-form natural laws from experimental data. Science 324(5923), 81–85 (2009)
Martius, G., Lampert, C.H.: Extrapolation and learning equations. arXiv preprint arXiv:1610.02995 (2016)
Berden, S., Kumar, M., Kolb, S., Guns, T.: Learning MAX-SAT models from examples using genetic algorithms and knowledge compilation. In: 28th International Conference on Principles and Practice of Constraint Programming (CP 2022). Schloss Dagstuhl-Leibniz-Zentrum für Informatik (2022)
Maragno, D., Wiberg, H., Bertsimas, D. Birbil, I., den Hertog, D., Fajemisin, A.O.: Mixed-iteger optimization with constraint learning. arXiv preprint arXiv:2111.04469 (2023)
Pawlak, T.P., Litwiniuk, B.: Ellipsoidal one-class constraint acquisition for quadratically constrained programming. Eur. J. Oper. Res. 294(1), 36–49 (2021)
Acknowledgements
This research was partially supported by the EU’s Horizon Digital, Industry, and Space program under grant agreement ID 101092989-DATAMITE. Additionally, we acknowledge Science Foundation Ireland under Grant No. 12/RC/2289 for funding the Insight Centre of Data Analytics (which is co-funded under the European Regional Development Fund).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vyhmeister, E., Paez, R., Gonzalez-Castane, G. (2024). Deep Neural Network for Constraint Acquisition Through Tailored Loss Function. In: Franco, L., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2024. ICCS 2024. Lecture Notes in Computer Science, vol 14836. Springer, Cham. https://doi.org/10.1007/978-3-031-63775-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-63775-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-63774-2
Online ISBN: 978-3-031-63775-9
eBook Packages: Computer ScienceComputer Science (R0)