Journal
NEURAL NETWORKS
Volume 141, Issue -, Pages 395-403Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2021.05.033
Keywords
Conditional; Generative adversarial network; Imputation; Missing data; Pseudo-label
Funding
- National Natural Sci-ence Foundation of China [11771257]
- Natural Science Foun-dation of Shandong Province [ZR2018MA008]
Ask authors/readers for more resources
This paper introduces a novel unsupervised missing data imputation method named PC-GAIN, which utilizes potential category information to enhance imputation power, significantly improving the imputation quality of GAIN. Experimental results demonstrate that PC-GAIN outperforms other baseline approaches on various benchmark datasets.
Datasets with missing values are very common in real world applications. GAIN, a recently proposed deep generative model for missing data imputation, has been proved to outperform many stateof-the-art methods. But GAIN only uses a reconstruction loss in the generator to minimize the imputation error of the non-missing part, ignoring the potential category information which can reflect the relationship between samples. In this paper, we propose a novel unsupervised missing data imputation method named PC-GAIN, which utilizes potential category information to further enhance the imputation power. Specifically, we first propose a pre-training procedure to learn potential category information contained in a subset of low-missing-rate data. Then an auxiliary classifier is determined using the synthetic pseudo-labels. Further, this classifier is incorporated into the generative adversarial framework to help the generator to yield higher quality imputation results. The proposed method can improve the imputation quality of GAIN significantly. Experimental results on various benchmark datasets show that our method is also superior to other baseline approaches. (C) 2021 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available