论文标题
通过概率缩减和样本重新加权改善GAN培训
Improving GAN Training with Probability Ratio Clipping and Sample Reweighting
论文作者
论文摘要
尽管在与视觉有关的广泛问题上取得了成功，但生成性的对抗网络（GAN）通常由于培训不稳定而遭受劣质性能，尤其是对于文本生成而言。为了解决这个问题，我们提出了一个新的变异GAN培训框架，该框架具有出色的训练稳定性。我们的方法灵感来自于各种观点下gan和增强学习的联系。连接导致（1）概率比率剪辑，使生成器训练规范以防止过度更新，以及（2）样本重新加权机制，通过淡化差异质量的假样本来改善歧视训练。此外，我们的变异GAN框架可以在许多gan中克服培训问题，即最佳歧视者无法为培训生成器提供任何信息梯度。通过插入各种最先进的gan体系结构中的训练方法，我们在多个任务中获得了显着提高的性能，包括文本生成，文本样式传输和图像生成。
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.
