Abstract
Adversarial learning stability is one of the difficulties of generative adversarial networks (GANs), which is closely related to networks convergence and generated images quality. For improving the stability, the multi-penalty functions GANs (MPF-GANs) is proposed. In this novel GANs, penalty function method is used to transform unconstrained GANs model into constrained model to improve adversarial learning stability and generated images quality. In optimization divergence tasks, two penalty divergences (Wassertein distance and Jensen-Shannon divergence) are added in addition to the main optimization divergence (reverse Kullback-Leibler divergence). In network structure, in order to realize the multi-divergence optimization tasks, the generator and discriminator are multi-task networks. Every generator subtask corresponds to a discriminator subtask to optimize the corresponding divergence. In CELEBA and CIFAR10 data sets, the experimental results show that although the number of parameters is increased, the adversarial learning stability and generated images quality are significantly improved. The performance of the novel GANs is better than most GANs models, close to state-of-the-art models, SAGANs and SNGANs.
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., et al.: Generative adversarial nets. In: International Conference on Neural Information Processing Systems, pp. 2672–2680 (2014)
Gui, J., Sun, Z.N., Wen, Y.G., et al.: A review on generative adversarial networks: algorithms, theory, and applications. arXiv:2001.06937v1 (2020)
Hong, Y.J., Hwang, U., Yoo, J., et al.: How generative adversarial networks and their variants work: an overview. ACM Comput. Surv. 52(1), Article 10, 1–43 (2019)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: International Conference on Learning Representations (2016)
Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein GAN. arXiv:1701.07875v3 (2017)
Gulrajani, I., Ahmed, F., Arjovsky, M., et al.: Improved training of Wasserstein GANs. In: International Conference on Neural Information Processing Systems, pp. 5769–5779 (2017)
Zhou, C.S., Zhang, J.S., Liu, J.M.: Lp-WGAN: using Lp-norm normalization to stabilize wasserstein generative adversarial networks. Knowl.-Based Syst. 161(2018), 415–424 (2018)
Berthelot, D., Schumm, T., Metz, L.: BEGAN: boundary equilibrium generative adversarial networks. arXiv:1703.10717v4 (2017)
Wu, J.Q., Huang, Z.W., Thoma, J., et al.: Wasserstein divergence for GANs. arXiv:1712.01026v4 (2018)
Su, J.L.: GAN-QP: a novel GAN framework without gradient vanishing and Lipschitz constraint. arXiv:1811.07296v2 (2018)
Basioti, K., Moustakides, G.V.: Designing GANs: a likelihood ratio approach. arXiv:2002.00865v2 (2020)
Mao, X.D., Li, Q., Xie, H.R., et al.: Least squares generative adversarial networks. In: IEEE International Conference on Computer Vision, pp. 2813–2821 (2017)
Nguyen, T.D., Le, T., Vu, H., et al.: Dual discriminator generative adversarial nets. In: International Conference on Neural Information Processing Systems (2017)
Miyato, T., Kataoka, T., Koyama, M., et al.: Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations (2018)
Su, J.L.: Training generative adversarial networks via turing test. arXiv:1810.10948v2 (2018)
Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. In: International Conference on Learning Representations (2019)
Peng, X.B., Kanazawa, A., Toyer, S., et al.: Variational discriminator bottleneck improving imitation learning, inverse RL, and GANs by constraining information flow. In: International Conference on Learning Representations (2019)
Denton, E., Chintala, S., Szlam, A., et al.: Deep generative image using a laplacian pyramid of adversarial networks. In: International Conference on Neural Information Processing Systems, pp. 1486–1494 (2015)
Karras, T., Aila, T., Laine, S., et al.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)
Karnewar, A., Wang, O.: MSG-GAN: multi-scale gradients for generative adversarial networks. In: International Conference on Computer Vision and Pattern Recognition, pp. 7799–7808 (2020)
Chu, C., Minami, K., Fukumizu, K.: Smoothness and stability in GANs. In: International Conference on Learning Representations (2020)
Zhang, H., Goodfellow, I., Metaxas, D., et al.: Self-attention generative adversarial networks. In: International Conference on Machine Learning (2019)
Chen, T., Zhai, X.H., Ritter, M., et al.: Self-supervised GANs via auxiliary rotation loss. In: IEEE Conference on Computer Vision and Pattern Recognition (2019)
Xiangli, Y.B., Deng, Y.B., Dai, B., et al.: Real or not real, that is the question. In: International Conference on Learning Representations (2020)
Fan, J.Q., Xue, L.Z., Zou, H.: Strong oracle optimality of folded concave penalized estimation. Ann. Stat. 42(3), 819–849 (2014)
Armand, P., Omheni, R.: A mixed logarithmic barrier-augmented lagrangian method for nonlinear optimization. J. Optim. Theory Appl. 173(2), 523–547 (2017)
Xu, X.S., Dang, C.Y., Chan, F.T.S., et al.: On smoothing L1 exact penalty function for constrained optimization problems. Numer. Funct. Anal. Optim. 40(1), 1–18 (2019)
Jayswal, A., Preeti: An exact L1 penalty function method for multi-dimensional first-order PDE constrained control optimization problem. Eur. J. Control 52(2020), 34–41 (2020)
Li, N., Yang, H.: Nonnegative estimation and variable selection under minimax concave penalty for sparse high-dimensional linear regression models. Stat. Pap. 62(2), 661–680 (2019). https://doi.org/10.1007/s00362-019-01107-w
Ruder, S.: An overview of multi-task learning in deep neural networks. arXiv:1706.05098v1 (2017)
Vandenhende, S., Georgoulis, S., Proesmans, M., et al.: Revisiting multi-task learning in the deep learning era. arXiv:2004.13379v1 (2020)
He, K.M., Zhang, X.Y., Ren, S.Q., et al.: Deep residual learning for image recognition. In: International Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Acknowledgments
This work is supported by National Natural Science Foundation of China (Grant Nos. U1936113 and 61872303).
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
Chen, H., He, H., Chen, F. (2021). Multi-penalty Functions GANs via Multi-task Learning. In: Sun, X., Zhang, X., Xia, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2021. Lecture Notes in Computer Science(), vol 12736. Springer, Cham. https://doi.org/10.1007/978-3-030-78609-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-78609-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78608-3
Online ISBN: 978-3-030-78609-0
eBook Packages: Computer ScienceComputer Science (R0)