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.
Robust Conformal Outlier Detection under Contaminated Reference Data
Department of Electrical and Computer Engineering, Technion IIT, Haifa, Israel(技术学院电子与计算机工程系);Department of Computer Science, Technion IIT, Haifa, Israel(技术学院计算机科学系);Department of Data Sciences and Operations, University of Southern California, Los Angeles, California, USA(南加州大学数据科学与运营系);Department of Computer Science, University of Southern California, Los Angeles, California, USA(南加州大学计算机科学系)
Robust Ordinal Embedding from Contaminated Relative Comparisons
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);University of Chinese Academy of Sciences(中国科学院大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)
Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach
Jet Propulsion Laboratory, California Institute of Technology(加州理工学院喷气推进实验室);Scientific Computing and Imaging Institute, University of Utah(犹他大学科学计算与影像研究所)