Abstract
Denoising Autoencoder Genetic Programming (DAE-GP) is a novel neural network-based estimation of distribution genetic programming (EDA-GP) algorithm that uses denoising autoencoder long short-term memory networks as a probabilistic model to replace the standard mutation and recombination operators of genetic programming (GP). At each generation, the idea is to flexibly identify promising properties of the parent population and to transfer these properties to the offspring where the DAE-GP uses denoising to make the model robust to noise that is present in the parent population. Denoising partially corrupts candidate solutions that are used as input to the model. The stronger the corruption, the stronger the generalization of the model. In this work, we study how corruption strength affects the exploration and exploitation behavior of the DAE-GP. For a generalization of the royal tree problem (high-locality problem), we find that the stronger the corruption, the stronger the exploration of the solution space. For the given problem, weak corruption resulting in a stronger exploitation of the solution space performs best. However, in more rugged fitness landscapes (low-locality problems), we expect that a stronger corruption resulting in a stronger exploration will be helpful. Choosing the right denoising strategy can therefore help to control the exploration and exploitation behavior in search, leading to an improved search quality.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Yao, L., Alain, G., Vincent, P.: Generalized denoising auto-encoders as generative models. In: Advances on Neural Information Processing Systems (NIPS 2013), vol. 26, pp. 899–907 (2013)
Chollet, F.: keras. https://github.com/fchollet/keras (2015)
Fortin, F.A., De Rainville, F.M., Gardner, M.A., Parizeau, M., Gagńe, C.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. 13(1), 2171–2175 (2012)
Hasegawa, Y., Iba, H.: Estimation of Bayesian network for program generation. In: Proceedings of the Third Asian-Pacific Workshop on Genetic Programming, pp. 35–46. Hanoi, Vietnam (2006)
Hasegawa, Y., Iba, H.: Estimation of distribution algorithm based on probabilistic grammar with latent annotations. In: Proceedings of the IEEE Congress on Evolutionary Computation, CEC 2007, pp. 1043–1050. IEEE (2007), https://doi.org/10.1109/CEC.2007.4424585
Hasegawa, Y., Iba, H.: A Bayesian network approach to program generation. IEEE Trans. Evol. Comput. 12(6), 750–764 (2008). https://doi.org/10.1109/tevc.2008.915999
Hemberg, E., Veeramachaneni, K., McDermott, J., Berzan, C., O’Reilly, U.M.: An investigation of local patterns for estimation of distribution genetic programming. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2012), pp. 767–774. ACM, Philadelphia (2012). https://doi.org/10.1145/2330163.2330270
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735
Kim, K., Shan, Y., Nguyen, X.H., McKay, R.I.: Probabilistic model building in genetic programming: a critical review. Gene. Program. Evol. Mach. 15(2), 115–167 (2013). https://doi.org/10.1007/s10710-013-9205-x
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations. San Diego (2015)
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, London (1992)
Kruskal, J.B.: An overview of sequence comparison: time warps, string edits, and macromolecules. Soc. Ind. Appl. Math. (SIAM) Rev. 25(2), 201–237 (1983). https://doi.org/10.1137/1025045
Pagie, L., Hogeweg, P.: Evolutionary consequences of coevolving targets. Evol. Comput. 5(4), 401–418 (1997)
Poli, R., McPhee, N.F.: A linear estimation-of-distribution GP system. In: Proceedings of the 11th European Conference on Genetic Programming (EuroGP 2008), pp. 206–217. Springer, Neapel (2008). https://doi.org/10.1007/978-3-540-78671-9
Probst, M.: Denoising autoencoders for fast combinatorial black box optimization. In: Proceedings of the Companion Publication of the Annual Conference on Genetic and Evolutionary Computation, pp. 1459–1460. ACM, Madrid (2015)
Probst, M., Rothlauf, F.: Harmless overfitting: Using denoising autoencoders in estimation of distribution algorithms. J. Mach. Learn. Res. 21(78), 1–31 (2020). http://jmlr.org/papers/v21/16-543.html
Punch, B., Zongker, D., Goodman, E.: The royal tree problem, a benchmark for single and multi-population genetic programming. In: Angeline, P.J., Kinnear, K.E., Jr. (eds.) Advances in Genetic Programming II, pp. 299–316. MIT Press, Cambridge (1996)
Ratle, A., Sebag, M.: Avoiding the bloat with stochastic grammar-based genetic programming. In: Collet, P., Fonlupt, C., Hao, J.-K., Lutton, E., Schoenauer, M. (eds.) EA 2001. LNCS, vol. 2310, pp. 255–266. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-46033-0_21
Rothlauf, F.: Design of Modern Heuristics: Principles and Application, 1st edn. Springer, Berlin (2011). https://doi.org/10.1007/978-3-540-72962-4
Salustowicz, R., Schmidhuber, J.: Probabilistic incremental program evolution. Evol. Comput. 5(2), 123–141 (1997). https://doi.org/10.1162/evco.1997.5.2.123
Shan, Y., McKay, R., Essam, D., Abbass, H.: A survey of probabilistic model building genetic programming. In: Pelikan, M., Sastry, K., CantúPaz, E. (eds.) Scalable Optimization via Probabilistic Modeling, pp. 121–160. Springer, Berlin (2006). https://doi.org/10.1007/978-3-540-34954-9
Srivastava, N., Mansimov, E., Salakhutdinov, R.: Unsupervised learning of video representations using LSTMs. In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), pp. 843–852. ACM, Lille (2015). https://doi.org/10.5555/3045118.3045209
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł, Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998–6008 (2017)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning (ICML 2008), pp. 1096–1103. ACM, Helsinki (2008). https://doi.org/10.1145/1390156.1390294
Wittenberg, D., Rothlauf, F., Schweim, D.: DAE-GP: denoising autoencoder LSTM networks as probabilistic models in estimation of distribution genetic programming. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 1037–1045. GECCO 2020, ACM, New York (2020). https://doi.org/10.1145/3377930.3390180
Wong, P.K., Lo, L.Y., Wong, M.L., Leung, K.S.: Grammar-based genetic programming with Bayesian network. In: IEEE Congress on Evolutionary Computation (CEC’14), pp. 739–746. IEEE, Beijing (2014)
Wong, P.K., Lo, L.Y., Wong, M.L., Leung, K.S.: Grammar-based genetic programming with dependence learning and Bayesian network classifier. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2014), pp. 959–966. ACM, Vancouver (2014). https://doi.org/10.1145/2576768.2598256
Yanai, K., Iba, H.: Estimation of distribution programming based on Bayesian network. In: IEEE Congress on Evolutionary Computation (CEC 2003), pp. 1618–1625. IEEE, Canberra (2003). https://doi.org/10.1109/CEC.2003.1299866
Acknowledgements
I thank my team in Mainz, especially Franz Rothlauf, for insightful discussions on this topic, as well as Dirk Schweim and Malte Probst for previous work on this topic.
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
Wittenberg, D. (2022). Using Denoising Autoencoder Genetic Programming to Control Exploration and Exploitation in Search. In: Medvet, E., Pappa, G., Xue, B. (eds) Genetic Programming. EuroGP 2022. Lecture Notes in Computer Science, vol 13223. Springer, Cham. https://doi.org/10.1007/978-3-031-02056-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-02056-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02055-1
Online ISBN: 978-3-031-02056-8
eBook Packages: Computer ScienceComputer Science (R0)