Abstract
A Generative Adversarial Network (GAN) is an unsupervised generative framework to generate a sample distribution that is identical to the data distribution. Recently, mix strategy multi-generator/discriminator GANs have been shown to outperform single pair GANs. However, the mixed model suffers from the problem of linearly growing training time. Also, imbalanced training among generators makes it difficult to parallelize. In this paper, we propose a balanced mix-generator GAN that works in parallel by mixing multiple disjoint generators to approximate the real distribution. The weights of the discriminator and the classifier are controlled by a balance strategy. We also present an efficient loss function, to force each generator to embrace few modes with a high probability. Our model is naturally adaptive to large parallel computation frameworks. Each generator can be trained on multiple GPUs asynchronously. We have performed extensive experiments on synthetic datasets, MNIST1000, CIFAR-10, and ImageNet. The results establish that our model can achieve the state-of-the-art performance (in terms of the modes coverage and the inception score), with significantly reduced training time. We also show that the missing mode problem can be relieved with a growing number of generators.
This work has been supported in part by the NSF grants 1447711 and 1743418.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. arXiv preprint arXiv:1701.04862 (2017)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein gan. arXiv preprint arXiv:1701.07875 (2017)
Arora, S., Ge, R., Liang, Y., Ma, T., Zhang, Y.: Generalization and equilibrium in generative adversarial nets (gans). arXiv preprint arXiv:1703.00573 (2017)
Berthelot, D., Schumm, T., Metz, L.: Began: Boundary equilibrium generative adversarial networks. arXiv preprint arXiv:1703.10717 (2017)
Che, T., Li, Y., Jacob, A.P., Bengio, Y., Li, W.: Mode regularized generative adversarial networks. arXiv preprint arXiv:1612.02136 (2016)
Durugkar, I., Gemp, I., Mahadevan, S.: Generative multi-adversarial networks. arXiv preprint arXiv:1611.01673 (2016)
Goodfellow, I.: Nips 2016 tutorial: Generative adversarial networks. arXiv preprint arXiv:1701.00160 (2016)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Hoang, Q., Nguyen, T.D., Le, T., Phung, D.: Multi-generator gernerative adversarial nets. arXiv preprint arXiv:1708.02556 (2017)
Metz, L., Poole, B., Pfau, D., Sohl-Dickstein, J.: Unrolled generative adversarial networks. arXiv preprint arXiv:1611.02163 (2016)
Nguyen, T.D., Le, T., Vu, H., Phung, D.: Dual discriminator generative adversarial nets. arXiv preprint arXiv:1709.03831 (2017)
Nowozin, S., Cseke, B., Tomioka, R.: F-GAN: training generative neural samplers using variational divergence minimization. In: Advances in Neural Information Processing Systems, pp. 271–279 (2016)
Okadome, Y., Wei, W., Aizono, T.: Parallel-pathway generator for generative adversarial networks to generate high-resolution natural images. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10614, pp. 655–662. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68612-7_74
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
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. 2234–2242 (2016)
Srivastava, A., Valkov, L., Russell, C., Gutmann, M., Sutton, C.: Veegan: Reducing mode collapse in gans using implicit variational learning. arXiv preprint arXiv:1705.07761 (2017)
Tolstikhin, I., Gelly, S., Bousquet, O., Simon-Gabriel, C.J., Schölkopf, B.: Adagan: Boosting generative models. arXiv preprint arXiv:1701.02386 (2017)
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
Xiao, X., Rajasekaran, S. (2018). PMGAN: Paralleled Mix-Generator Generative Adversarial Networks with Balance Control. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11141. Springer, Cham. https://doi.org/10.1007/978-3-030-01424-7_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-01424-7_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01423-0
Online ISBN: 978-3-030-01424-7
eBook Packages: Computer ScienceComputer Science (R0)