Improving GAN Training with Probability Ratio Clipping and Sample Reweighting

• URL: http://arxiv.org/abs/2006.06900v4
• Date: Fri, 30 Oct 2020 16:27:22 GMT
• Title: Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
• Authors: Yue Wu, Pan Zhou, Andrew Gordon Wilson, Eric P. Xing, Zhiting Hu
• Abstract summary: generative adversarial networks (GANs) often suffer from inferior performance due to unstable training. We propose a new variational GAN training framework which enjoys superior training stability. By plugging the training approach in diverse state-of-the-art GAN architectures, we obtain significantly improved performance over a range of tasks.
• Score: 145.5106274085799
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new variational GAN training framework which enjoys superior training stability. Our approach is inspired by a connection of GANs and reinforcement learning under a variational perspective. The connection leads to (1) probability ratio clipping that regularizes generator training to prevent excessively large updates, and (2) a sample re-weighting mechanism that improves discriminator training by downplaying bad-quality fake samples. Moreover, our variational GAN framework can provably overcome the training issue in many GANs that an optimal discriminator cannot provide any informative gradient to training generator. By plugging the training approach in diverse state-of-the-art GAN architectures, we obtain significantly improved performance over a range of tasks, including text generation, text style transfer, and image generation.

Related papers

• Parallelly Tempered Generative Adversarial Networks [7.94957965474334]
  A generative adversarial network (GAN) has been a representative backbone model in generative artificial intelligence (AI) This work analyzes the training instability and inefficiency in the presence of mode collapse by linking it to multimodality in the target distribution. With our newly developed GAN objective function, the generator can learn all the tempered distributions simultaneously.
  arXiv  Detail & Related papers  (2024-11-18T18:01:13Z)
• Improving GAN Training via Feature Space Shrinkage [69.98365478398593]
  We propose AdaptiveMix, which shrinks regions of training data in the image representation space of the discriminator. Considering it is intractable to directly bound feature space, we propose to construct hard samples and narrow down the feature distance between hard and easy samples. The evaluation results demonstrate that our AdaptiveMix can facilitate the training of GANs and effectively improve the image quality of generated samples.
  arXiv  Detail & Related papers  (2023-03-02T20:22:24Z)
• SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks [28.261911789087463]
  We introduce several improvements to the GAN training schemes, which can be applied to most GAN-based SE models. We present self-correcting optimization for training a GAN discriminator on SE tasks, which helps avoid "harmful" training directions. We have tested our proposed methods on several state-of-the-art GAN-based SE models and obtained consistent improvements.
  arXiv  Detail & Related papers  (2022-10-26T04:48:40Z)
• Enhancing Adversarial Training with Feature Separability [52.39305978984573]
  We introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to boost the intra-class feature similarity and increase inter-class feature variance. Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.
  arXiv  Detail & Related papers  (2022-05-02T04:04:23Z)
• Training Generative Adversarial Networks in One Stage [58.983325666852856]
  We introduce a general training scheme that enables training GANs efficiently in only one stage. We show that the proposed method is readily applicable to other adversarial-training scenarios, such as data-free knowledge distillation.
  arXiv  Detail & Related papers  (2021-02-28T09:03:39Z)
• Evolving GAN Formulations for Higher Quality Image Synthesis [15.861807854144228]
  Generative Adversarial Networks (GANs) have extended deep learning to complex generation and translation tasks. GANs are notoriously difficult to train: Mode collapse and other instabilities in the training process often degrade the quality of the generated results. This paper presents a new technique called TaylorGAN for improving GANs by discovering customized loss functions for each of its two networks.
  arXiv  Detail & Related papers  (2021-02-17T05:11:21Z)
• Self-Progressing Robust Training [146.8337017922058]
  Current robust training methods such as adversarial training explicitly uses an "attack" to generate adversarial examples. We propose a new framework called SPROUT, self-progressing robust training. Our results shed new light on scalable, effective and attack-independent robust training methods.
  arXiv  Detail & Related papers  (2020-12-22T00:45:24Z)
• Improving the Speed and Quality of GAN by Adversarial Training [87.70013107142142]
  We develop FastGAN to improve the speed and quality of GAN training based on the adversarial training technique. Our training algorithm brings ImageNet training to the broader public by requiring 2-4 GPUs.
  arXiv  Detail & Related papers  (2020-08-07T20:21:31Z)
• InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning [39.316605441868944]
  Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications. We propose a principled framework to simultaneously mitigate two fundamental issues in GANs: catastrophic forgetting of the discriminator and mode collapse of the generator. Our approach significantly stabilizes GAN training and improves GAN performance for image synthesis across five datasets.
  arXiv  Detail & Related papers  (2020-07-09T06:56:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.