Variational cycle-consistent imputation adversarial networks for general missing patterns

作者：

Highlights：

• Discover the true distribution of general missing patterns.

• Present variational cycle-consistent imputation adversarial networks.

• A theoretical analysis of the method is provided.

• Performed an empirical study on various imputation problems.

• Proposed method delivers the state-of-the-art performance.

摘要

•Discover the true distribution of general missing patterns.•Present variational cycle-consistent imputation adversarial networks.•A theoretical analysis of the method is provided.•Performed an empirical study on various imputation problems.•Proposed method delivers the state-of-the-art performance.

论文关键词：Imputation,Missing data,Cycle-consistent

论文评审过程：Received 20 October 2020, Revised 2 September 2021, Accepted 18 April 2022, Available online 20 April 2022, Version of Record 2 May 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108720