arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.01722cs.LG
收藏

利用污染数据集和纯化生成对抗网络学习干净数据分布

Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks

Sun Yat-sen University(中山大学);Guangdong Key Laboratory of Big Data Analysis and Processing(广东省大数据分析与处理重点实验室)

Bowen Tian, Qinliang Su, Jianxing Yu

摘要:

生成对抗网络(GANs)以其强大的捕获训练实例底层分布的能力而闻名。自从GAN的开创性工作以来,已经提出了GAN的许多变体。然而,现有的GANs几乎都是建立在训练数据集是干净的假设之上的。但在许多现实世界的应用中,这可能不成立,也就是说,训练数据集可能被一部分不需要的实例污染。当在这样的数据集上训练时,现有的GANs将学习期望和污染实例的混合分布,而不是仅期望数据的期望分布(目标分布)。为了从污染数据集中学习目标分布,开发了两个纯化的生成对抗网络(PuriGAN),其中鉴别器通过利用仅由污染实例组成的额外数据集来增强区分目标和污染实例的能力。我们证明,在一些温和的条件下,提出的PuriGAN保证收敛到所需实例的分布。在几个数据集上的实验结果表明,当在受污染的数据集上训练时,所提出的PuriGAN能够从所需的分布中生成比可比基线更好的图像。此外,我们还通过将其应用于污染数据集和PU学习的半监督异常检测任务,证明了PuriGAN在下游应用中的有用性。实验结果表明,PuriGAN能够在这两个任务上提供超过可比基线的最佳性能。

英文摘要:

Generative adversarial networks (GANs) are known for their strong abilities on capturing the underlying distribution of training instances. Since the seminal work of GAN, many variants of GAN have been proposed. However, existing GANs are almost established on the assumption that the training dataset is clean. But in many real-world applications, this may not hold, that is, the training dataset may be contaminated by a proportion of undesired instances. When training on such datasets, existing GANs will learn a mixture distribution of desired and contaminated instances, rather than the desired distribution of desired data only (target distribution). To learn the target distribution from contaminated datasets, two purified generative adversarial networks (PuriGAN) are developed, in which the discriminators are augmented with the capability to distinguish between target and contaminated instances by leveraging an extra dataset solely composed of contamination instances. We prove that under some mild conditions, the proposed PuriGANs are guaranteed to converge to the distribution of desired instances. Experimental results on several datasets demonstrate that the proposed PuriGANs are able to generate much better images from the desired distribution than comparable baselines when trained on contaminated datasets. In addition, we also demonstrate the usefulness of PuriGAN on downstream applications by applying it to the tasks of semi-supervised anomaly detection on contaminated datasets and PU-learning. Experimental results show that PuriGAN is able to deliver the best performance over comparable baselines on both tasks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑