论文标题
通过记忆拒绝来减少gan中的训练样本记忆
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection
论文作者
论文摘要
由于其高发质量，生成的对抗网络（GAN）仍然是流行的研究方向。可以观察到，许多最先进的甘恩生成的样品与训练集更相似，而不是相同分布中的固定测试集，暗示某些训练样本在这些模型中被隐含地记住。在许多应用程序中，这种记忆行为是不利的，这些应用要求生成的样品与已知样品完全不同。然而，尚不清楚在不损害发电质量的情况下是否可以减少记忆。在本文中，我们提出了记忆拒绝，这是一种培训计划，该计划拒绝生成的样本，这些样本是培训期间近乎培训样本的近乎培训。我们的方案很简单，通用，可以直接应用于任何GAN体系结构。在多个数据集和GAN模型上进行的实验验证了记忆拒绝有效地减少了训练样本记忆，并且在许多情况下，不会牺牲生成质量。可以在$ \ texttt {https://github.com/jybai/mrgan} $上找到重现实验结果的代码。
Generative adversarial network (GAN) continues to be a popular research direction due to its high generation quality. It is observed that many state-of-the-art GANs generate samples that are more similar to the training set than a holdout testing set from the same distribution, hinting some training samples are implicitly memorized in these models. This memorization behavior is unfavorable in many applications that demand the generated samples to be sufficiently distinct from known samples. Nevertheless, it is unclear whether it is possible to reduce memorization without compromising the generation quality. In this paper, we propose memorization rejection, a training scheme that rejects generated samples that are near-duplicates of training samples during training. Our scheme is simple, generic and can be directly applied to any GAN architecture. Experiments on multiple datasets and GAN models validate that memorization rejection effectively reduces training sample memorization, and in many cases does not sacrifice the generation quality. Code to reproduce the experiment results can be found at $\texttt{https://github.com/jybai/MRGAN}$.
