# Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems

arXiv: https://arxiv.org/abs/2004.02584 · HTML: https://mlsanity.com/paper/2004.02584/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques](https://mlsanity.com/paper/2210.08258/) (2022)
- [An Additive Autoencoder for Dimension Estimation](https://mlsanity.com/paper/2210.06773/) (2022)
- [Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation](https://mlsanity.com/paper/2409.08917/) (2024)
- [Deep Symmetric Autoencoders from the Eckart-Young-Schmidt Perspective](https://mlsanity.com/paper/2506.11641/) (2025)
- [Towards Bridging Review Sparsity in Recommendation with Textual Edge Graph Representation](https://mlsanity.com/paper/2508.01128/) (2025)
- [Dealing with missing data using attention and latent space regularization](https://mlsanity.com/paper/2211.07059/) (2022)

## Abstract (arXiv)

Dealing with missing data in data analysis is inevitable. Although powerful imputation methods that address this problem exist, there is still much room for improvement. In this study, we examined single imputation based on deep autoencoders, motivated by the apparent success of deep learning to efficiently extract useful dataset features. We have developed a consistent framework for both training and imputation. Moreover, we benchmarked the results against state-of-the-art imputation methods on different data sizes and characteristics. The work was not limited to the one-type variable dataset; we also imputed missing data with multi-type variables, e.g., a combination of binary, categorical, and continuous attributes. To evaluate the imputation methods, we randomly corrupted the complete data, with varying degrees of corruption, and then compared the imputed and original values. In all experiments, the developed autoencoder obtained the smallest error for all ranges of initial data corruption.