Abstract
This article presents a parallel/distributed methodology for the intelligent search of the hyperparameters configuration for generative artificial neural networks (GANs). Finding the configuration that best fits a GAN for a specific problem is challenging because GANs simultaneously train two deep neural networks. Thus, in general, GANs have more configuration parameters than other deep learning methods. The proposed system applies the iterated racing approach taking advantage of parallel/distributed computing for the efficient use of resources for configuration. The main results of the experimental evaluation performed on the MNIST dataset showed that the parallel system is able to efficiently use the GPU, achieving a high level of parallelism and reducing the computational wall clock time by 78%, while providing competitive comparable results to the sequential hyperparameters search.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akay, B., Karaboga, D., Akay, R.: A comprehensive survey on optimizing deep learning models by metaheuristics. Artificial Intelligence Review, pp. 1–66 (2021)
Al-Dujaili, A., Schmiedlechner, T., Hemberg, E., O’Reilly, U.M.: Towards distributed coevolutionary GANs. In: AAAI Symposium (2018)
Bergstra, J., Bardenet, R., Bengio, Y., Kégl, B.: Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems, vol. 24 (2011)
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. Journal of Machine Learning Research, vol. 13, no. 2 (2012)
Birattari, M., Stützle, T., Paquete, L., Varrentrapp, K., et al.: A racing algorithm for configuring metaheuristics. In: Gecco, vol. 2 (2002)
Camero, A., Toutouh, J., Alba, E.: Random error sampling-based recurrent neural network architecture optimization. Eng. Appl. Artif. Intell. 96, 103946 (2020)
Camero, A., Toutouh, J., Stolfi, D.H., Alba, E.: Evolutionary deep learning for car park occupancy prediction in smart cities. In: Battiti, R., Brunato, M., Kotsireas, I., Pardalos, P.M. (eds.) LION 12 2018. LNCS, vol. 11353, pp. 386–401. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05348-2_32
Gitler, I., Gomes, A.T.A., Nesmachnow, S.: The latin american supercomputing ecosystem for science. Commun. ACM 63(11), 66–71 (2020)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Hemberg, E., Toutouh, J., Al-Dujaili, A., Schmiedlechner, T., O’Reilly U-M.: Spatial coevolution for generative adversarial network training. ACM Trans. Evol. Learn. Optim. 2(1) (2021). Article 6, 28 p. https://doi.org/10.1145/3458845
Hinz, T., Navarro-Guerrero, N., Magg, S., Wermter, S.: Speeding up the hyperparameter optimization of deep convolutional neural networks. Int. J. Comput. Intell. Appl. 17(02), 1850008 (2018)
Kaselimi, M., Doulamis, N., Doulamis, A., Voulodimos, A., Protopapadakis, E.: Bayesian-optimized bidirectional lstm regression model for non-intrusive load monitoring. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2747–2751 (2019). https://doi.org/10.1109/ICASSP.2019.8683110
López-Ibáñez, M., Dubois-Lacoste, J., Cáceres, L.P., Birattari, M., Stützle, T.: The IRACE package: iterated racing for automatic algorithm configuration. Oper. Res. Perspect. 3, 43–58 (2016)
Lopez-Ibanez, M., Stutzle, T.: The automatic design of multiobjective ant colony optimization algorithms. IEEE Trans. Evol. Comput. 16(6), 861–875 (2012)
López-Ibánez, M., Stützle, T.: Automatically improving the anytime behaviour of optimisation algorithms. Eur. J. Oper. Res. 235(3), 569–582 (2014)
Lopez-Rincon, A., Tonda, A., Elati, M., Schwander, O., Piwowarski, B., Gallinari, P.: Evolutionary optimization of convolutional neural networks for cancer mirna biomarkers classification. Appl. Soft Comput. 65, 91–100 (2018)
Nesmachnow, S., Iturriaga, S.: Cluster-UY: collaborative scientific high performance computing in uruguay. In: Torres, M., Klapp, J. (eds.) ISUM 2019. CCIS, vol. 1151, pp. 188–202. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-38043-4_16
Pan, Z., Yu, W., Yi, X., Khan, A., Yuan, F., Zheng, Y.: Recent progress on generative adversarial networks (GANs): a survey. IEEE Access 7, 36322–36333 (2019)
Prestes, L., Delgado, M.R., Lüders, R., Gonçalves, R., Almeida, C.P.: Boosting the performance of moea/d-dra with a multi-objective hyper-heuristic based on irace and ucb method for heuristic selection. In: 2018 IEEE Congress on Evolutionary Computation (CEC), pp. 1–8. IEEE (2018)
Schmiedlechner, T., Yong, I., Al-Dujaili, A., Hemberg, E., O’Reilly, U.: Lipizzaner: a system that scales robust generative adversarial network training. In: 32\(^{nd}\) Conference on Neural Information Processing Systems (2018)
Schmiedlechner, T., Yong, I.N.Z., Al-Dujaili, A., Hemberg, E., O’Reilly, U.M.: Lipizzaner: a system that scales robust generative adversarial network training. In: the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) Workshop on Systems for ML and Open Source Software (2018)
Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-weka: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 847–855 (2013)
Toutouh, J., Esteban, M., Nesmachnow., S.: Parallel/distributed generative adversarial neural networks for data augmentation of covid-19 training images. In: Latin America High Performance Computing Conference (CARLA 2020), p. 10 (2020)
Toutouh, J., Esteban, M., Nesmachnow, S.: Parallel/distributed generative adversarial neural networks for data augmentation of COVID-19 training images. In: Nesmachnow, S., Castro, H., Tchernykh, A. (eds.) CARLA 2020. CCIS, vol. 1327, pp. 162–177. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-68035-0_12
Toutouh, J., Hemberg, E., O’Reilly, U.M.: Spatial evolutionary generative adversarial networks. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 472–480. GECCO ’19, Association for Computing Machinery, New York, NY, USA (2019)
Toutouh, J., Hemberg, E., O’Reilly, U.-M.: Data dieting in GAN training. In: Iba, H., Noman, N. (eds.) Deep Neural Evolution. NCS, pp. 379–400. Springer, Singapore (2020). https://doi.org/10.1007/978-981-15-3685-4_14
Ugolotti, R., Nashed, Y.S., Mesejo, P., Cagnoni, S.: Algorithm configuration using gpu-based metaheuristics. In: Proceedings of the 15th Annual Conference Companion on Genetic and Evolutionary Computation, pp. 221–222 (2013)
Victoria, A.H., Maragatham, G.: Automatic tuning of hyperparameters using bayesian optimization. Evolving Syst. 12, 217–223 (2021)
Wang, C., Xu, C., Yao, X., Tao, D.: Evolutionary generative adversarial networks. IEEE Trans. Evol. Comput. 23(6), 921–934 (2019)
Wu, J., Chen, X.Y., Zhang, H., Xiong, L.D., Lei, H., Deng, S.H.: Hyperparameter optimization for machine learning models based on bayesian optimization. J. Electron. Sci. Technol. 17(1), 26–40 (2019)
Yang, L., Shami, A.: On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415, 295–316 (2020)
Acknowledgements
This research was partially funded by European Union’s Horizon 2020 research and innovation program under the Marie SkÅ‚odowska-Curie grant agreement No 799078 and by the European Union H2020-ICT-2019-3.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Esteban, M., Toutouh, J., Nesmachnow, S. (2021). Parallel/Distributed Intelligent Hyperparameters Search for Generative Artificial Neural Networks. In: Jagode, H., Anzt, H., Ltaief, H., Luszczek, P. (eds) High Performance Computing. ISC High Performance 2021. Lecture Notes in Computer Science(), vol 12761. Springer, Cham. https://doi.org/10.1007/978-3-030-90539-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-90539-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90538-5
Online ISBN: 978-3-030-90539-2
eBook Packages: Computer ScienceComputer Science (R0)