Abstract
Generative Adversarial Networks (or called GANs) is a generative type of model which can be used to generate new data points from the given initial dataset. In this paper, the training problems of GANs such as ‘vanishing gradient’ and ‘mode collapse’ are reduced using the proposed EVGAN which stands for ‘evolving GAN’. An improvement was done with the help of using Wasserstein loss function instead of the Minimax loss in the traditional GAN. Also, coevolution ensures that the best models from both the generator and discriminator pool are selected for further evolution thereby making the training of GAN more stable. Speciation is also included with a threshold of min. no of species thereby helping in increasing the diversity of the generated image. The model is evaluated in the MNIST dataset and shows better performance in accuracy as well as convergence when compared to the traditional GAN and WGAN.
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
References
Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Proceedings of NIPS, vol. 27, pp. 2672–2680 (2014)
Goodfellow, I.: NIPS 2016 tutorial: generative adversarial networks (2016). arXiv preprint arXiv:1701.00160
Fedus, W., Rosca, M., Lakshminarayanan, B., Dai, A.M., Mohamed, S., Goodfellow, I.: Many paths to equilibrium: GANs do not need to decrease a divergence at every step. In: Proceedings of ICLR 2018 (2018)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: Conference paper at ICLR 2016 (2016)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: Proceedings of CVPR (2017)
Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. Published as a conference paper at ICLR (2018)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. In: Proceedings of MLR 2017
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: improved training of Wasserstein GANs. In: NIPS proceedings, pp. 1767–1777 (2017)
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training Gans. In: Advances in Neural Information Processing Systems, pp. 2226–2234 (2016)
Liu, S., Bousquet, O., Chaudhuri, K.:. Approximation and convergence properties of generative adversarial learning (2017). arXiv preprint arXiv:1705.08991
Wang, C., Xu, C., Yao, X., Tao, D.: Evolutionary generative adversarial networks. Proc. IEEE 23(6), 921–934 (2019)
Costa, V., Lourenço, N., Machado, P.: Coevolution of generative adversarial networks. In: International Conference on the Applications of Evolutionary Computation, pp. 473–487. Springer (2019)
Nambiar, S., Jeyakumar, G.: Co-operative Co-evolution based hybridization of differential evolution and particle swarm optimization algorithms in distributed environment. In: Emerging Research in Computing, Information, Communication and Applications: ERCICA 2015, vol. 2. Springer India, New Delhi, pp. 175–187 (2015)
Sree, K., Jeyakumar, G.: An evolutionary computing approach to solve object identification problem in image processing applications. J. Comput. Theor. Nanosci. 17, 439–444 (2020)
Reddy, R.R., Jeyakumar, G.: Differential evolution with added components for early detection and avoidance of premature convergence in solving unconstrained global optimization problems. Int. J. Appl. Eng. Res. 10(5), 13579–13594 (2015)
Costa, V., Lourenco, N., Machado, P.: Exploring the evolution of GANs through quality diversity. In: GECCO (2020)
Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality stability and variation. In: Proceedings of International Conference on Learning Representations (ICLR), pp. 1–26 (2018)
Dhanalakshmy, D.M., Pranav, P., Jeyakumar, G.: A survey on adaptation strategies for mutation and crossover rates of differential evolution algorithm. Int. J. Adv. Sci. Eng. Inf. Technol. (IJASEIT) (Scopus) 6(5), 613–623 (2016)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nair, V.K., Shunmuga Velayutham, C. (2022). EVGAN: Optimization of Generative Adversarial Networks Using Wasserstein Distance and Neuroevolution. In: Suma, V., Fernando, X., Du, KL., Wang, H. (eds) Evolutionary Computing and Mobile Sustainable Networks. Lecture Notes on Data Engineering and Communications Technologies, vol 116. Springer, Singapore. https://doi.org/10.1007/978-981-16-9605-3_4
Download citation
DOI: https://doi.org/10.1007/978-981-16-9605-3_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9604-6
Online ISBN: 978-981-16-9605-3
eBook Packages: EngineeringEngineering (R0)