On oversampling imbalanced data with deep conditional generative models

作者：

Highlights：

• Propose the conditional Variational Autoencoder for the imbalance problem.

• Deep conditional generative models can improve accuracy in imbalanced learning.

• Variational Autoencoders achieve better results than Generative Adversarial Networks.

• Random oversampling prior to training generative models often lead to better results.

摘要

•Propose the conditional Variational Autoencoder for the imbalance problem.•Deep conditional generative models can improve accuracy in imbalanced learning.•Variational Autoencoders achieve better results than Generative Adversarial Networks.•Random oversampling prior to training generative models often lead to better results.

论文关键词：Deep generative models,Conditional variational autoencoders,Class imbalance,Oversampling

论文评审过程：Received 1 August 2019, Revised 4 December 2020, Accepted 4 December 2020, Available online 13 December 2020, Version of Record 24 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114463