Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flow

In this paper, we investigate the training process of generative networks that use a type of probability density distance named particle-based distance as the objective function, e.g. MMD GAN, Cram\'er GAN, EIEG GAN. However, these GANs often suffer from the problem of unstable training. In this paper, we analyze the stability of the training process of these GANs from the perspective of probability density dynamics. In our framework, we regard the discriminator $D$ in these GANs as a feature transformation mapping that maps high dimensional data into a feature space, while the generator $G$ maps random variables to samples that resemble real data in terms of feature space. This perspective enables us to perform stability analysis for the training of GANs using the Wasserstein gradient flow of the probability density function. We find that the training process of the discriminator is usually unstable due to the formulation of $\min_G \max_D E(G, D)$ in GANs. To address this issue, we add a stabilizing term in the discriminator loss function. We conduct experiments to validate our stability analysis and stabilizing method.

[1]  Yue Wu,et al.  Elastic Interaction Energy-Based Generative Model: Approximation in Feature Space , 2023, ArXiv.

[2]  Hong-Han Shuai,et al.  Gradient Normalization for Generative Adversarial Networks , 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

[3]  Youssef Mroueh,et al.  On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow , 2020, AISTATS.

[4]  T. Luo,et al.  Energy Scaling and Asymptotic Properties of One-Dimensional Discrete System with Generalized Lennard-Jones (m, n) Interaction , 2020, Journal of nonlinear science.

[5]  Wenming Tang,et al.  Spectral Regularization for Combating Mode Collapse in GANs , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[6]  Dávid Terjék Adversarial Lipschitz Regularization , 2019, ICLR.

[7]  Truyen Tran,et al.  Improving Generalization and Stability of Generative Adversarial Networks , 2019, ICLR.

[8]  Wei Wang,et al.  Improving MMD-GAN Training with Repulsive Loss Function , 2018, ICLR.

[9]  Arthur Gretton,et al.  On gradient regularizers for MMD GANs , 2018, NeurIPS.

[10]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[11]  Jacob Abernethy,et al.  On Convergence and Stability of GANs , 2018 .

[12]  Rishi Sharma,et al.  A Note on the Inception Score , 2018, ArXiv.

[13]  Arthur Gretton,et al.  Demystifying MMD GANs , 2018, ICLR.

[14]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[15]  Marc G. Bellemare,et al.  The Cramer Distance as a Solution to Biased Wasserstein Gradients , 2017, ArXiv.

[16]  Sebastian Nowozin,et al.  Stabilizing Training of Generative Adversarial Networks through Regularization , 2017, NIPS.

[17]  Yiming Yang,et al.  MMD GAN: Towards Deeper Understanding of Moment Matching Network , 2017, NIPS.

[18]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[19]  Léon Bottou,et al.  Towards Principled Methods for Training Generative Adversarial Networks , 2017, ICLR.

[20]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

[22]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[24]  Kenji Fukumizu,et al.  Equivalence of distance-based and RKHS-based statistics in hypothesis testing , 2012, ArXiv.

[25]  Yang Xiang,et al.  Misfit elastic energy and a continuum model for epitaxial growth with elasticity on vicinal surfaces , 2004 .

[26]  J. Lennard-jones,et al.  On the Forces between Atoms and Ions , 1925 .

[27]  D. Kinderlehrer,et al.  THE VARIATIONAL FORMULATION OF THE FOKKER-PLANCK EQUATION , 1996 .