Abstract
Many attempts have been made to apply machine learning techniques to constraint satisfaction problems (CSPs). However, none of them have made use of the recent advances in deep learning. In this paper, we apply deep learning to predict the satisfiabilities of CSPs. To the best of our knowledge, this is the first effective application of deep learning to CSPs that yields \({>}99.99\%\) prediction accuracy on random Boolean binary CSPs whose constraint tightnesses or constraint densities do not determine their satisfiabilities. We use a deep convolutional neural network on a matrix representation of CSPs. Since it is NP-hard to solve CSPs, labeled data required for training are in general costly to produce and are thus scarce. We address this issue using the asymptotic behavior of generalized Model A, a new random CSP generation model, along with domain adaptation and data augmentation techniques for CSPs. We demonstrate the effectiveness of our deep learning techniques using experiments on random Boolean binary CSPs. While these CSPs are known to be in P, we use them for a proof of concept.
The research at the University of Southern California (USC) was supported by National Science Foundation (NSF) under grant numbers 1724392, 1409987, and 1319966.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Another related work [9] using a different approach was only publicly available after this paper was accepted, before which we had no access to it. Nevertheless, it only demonstrated low training and test accuracies in the experiments when the number of variables in a CSP is non-trivial (\({\ge }5\)) and we do not consider it effective (yet).
References
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. software (2015). https://www.tensorflow.org/
Achlioptas, D., Molloy, M.S.O., Kirousis, L.M., Stamatiou, Y.C., Kranakis, E., Krizanc, D.: Random constraint satisfaction: a more accurate picture. Constraints 6(4), 329–344 (2001). https://doi.org/10.1023/A:1011402324562
Amadini, R., Gabbrielli, M., Mauro, J.: An empirical evaluation of portfolios approaches for solving CSPs. In: The International Conference on Integration of Artificial Intelligence and Operations Research Techniques in Constraint Programming, pp. 316–324 (2013). https://doi.org/10.1007/978-3-642-38171-3_21
Amadini, R., Gabbrielli, M., Mauro, J.: An enhanced features extractor for a portfolio of constraint solvers. In: The Annual ACM Symposium on Applied Computing, pp. 1357–1359 (2014). https://doi.org/10.1145/2554850.2555114
Arbelaez, A., Hamadi, Y., Sebag, M.: Continuous search in constraint programming. In: The IEEE International Conference on Tools with Artificial Intelligence, pp. 53–60 (2010). https://doi.org/10.1109/ICTAI.2010.17
Bourlard, H.A., Morgan, N.: Connectionist Speech Recognition. Springer, New York (1994). https://doi.org/10.1007/978-1-4615-3210-1
Chollet, F., et al.: Keras (2015). https://keras.io
Ciregan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: The IEEE Conference on Computer Vision and Pattern Recognition, pp. 3642–3649 (2012). https://doi.org/10.1109/CVPR.2012.6248110
Galassi, A., Lombardi, M., Mello, P., Milano, M.: Model agnostic solution of CSPs via deep learning: a preliminary study. In: The International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pp. 254–262 (2018). https://doi.org/10.1007/978-3-319-93031-2_18
Gent, I.P., et al.: Learning when to use lazy learning in constraint solving. In: The European Conference on Artificial Intelligence, pp. 873–878 (2010). https://doi.org/10.3233/978-1-60750-606-5-873
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Guerri, A., Milano, M.: Learning techniques for automatic algorithm portfolio selection. In: The European Conference on Artificial Intelligence, pp. 475–479 (2004)
Hahnloser, R.H.R., Sarpeshkar, R., Mahowald, M.A., Douglas, R.J., Seung, H.S.: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405, 947–951 (2000). https://doi.org/10.1038/35016072
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: The IEEE International Conference on Computer Vision, pp. 1026–1034 (2015). https://doi.org/10.1109/ICCV.2015.123
Kadioglu, S., Malitsky, Y., Sellmann, M., Tierney, K.: ISAC - instance-specific algorithm configuration. In: The European Conference on Artificial Intelligence, pp. 751–756 (2010). https://doi.org/10.3233/978-1-60750-606-5-751
Kotthoff, L.: Algorithm selection for combinatorial search problems: a survey. In: Data Mining and Constraint Programming: Foundations of a Cross-Disciplinary Approach, pp. 149–190 (2016). https://doi.org/10.1007/978-3-319-50137-6_7
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: The Neural Information Processing Systems Conference, pp. 1097–1105 (2012). https://doi.org/10.1145/3065386
LeCun, Y.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989). https://doi.org/10.1162/neco.1989.1.4.541
Loreggia, A., Malitsky, Y., Samulowitz, H., Saraswat, V.: Deep learning for algorithm portfolios. In: The AAAI Conference on Artificial Intelligence, pp. 1280–1286 (2016)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: The International Conference on Machine Learning, pp. 2014–2023 (2016)
O’Mahony, E., Hebrard, E., Holland, A., Nugent, C., O’Sullivan, B.: Using case-based reasoning in an algorithm portfolio for constraint solving. In: The Irish Conference on Artificial Intelligence and Cognitive Science (2008)
Prud’homme, C., Fages, J.G., Lorca, X.: Choco Documentation. TASC - LS2N CNRS UMR 6241, COSLING S.A.S. (2017). http://www.choco-solver.org
Pulina, L., Tacchella, A.: A multi-engine solver for quantified Boolean formulas. In: The International Conference on Principles and Practice of Constraint Programming, pp. 574–589 (2007). https://doi.org/10.1007/978-3-540-74970-7_41
Sateesh Babu, G., Zhao, P., Li, X.L.: Deep convolutional neural network based regression approach for estimation of remaining useful life. In: The International Conference on Database Systems for Advanced Applications, pp. 214–228 (2016). https://doi.org/10.1007/978-3-319-32025-0_14
Selsam, D., Lamm, M., Bünz, B., Liang, P., de Moura, L., Dill, D.L.: Learning a SAT solver from single-bit supervision. arXiv:1802.03685 [cs.AI] (2018)
Smith, B.M., Dyer, M.E.: Locating the phase transition in binary constraint satisfaction problems. Artif. Intell. 81(1), 155–181 (1996). https://doi.org/10.1016/0004-3702(95)00052-6
Xu, L., Hutter, F., Hoos, H.H., Leyton-Brown, K.: SATzilla: portfolio-based algorithm selection for SAT. J. Artif. Intell. Res. 32, 565–606 (2008). https://doi.org/10.1613/jair.2490
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, H., Koenig, S., Kumar, T.K.S. (2018). Towards Effective Deep Learning for Constraint Satisfaction Problems. In: Hooker, J. (eds) Principles and Practice of Constraint Programming. CP 2018. Lecture Notes in Computer Science(), vol 11008. Springer, Cham. https://doi.org/10.1007/978-3-319-98334-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-98334-9_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98333-2
Online ISBN: 978-3-319-98334-9
eBook Packages: Computer ScienceComputer Science (R0)