# MisConv: Convolutional Neural Networks for Missing Data

arXiv: https://arxiv.org/abs/2110.14010 · HTML: https://mlsanity.com/paper/2110.14010/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 58 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Wasserstein Auto-Encoders](https://mlsanity.com/paper/1711.01558/) (2017)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [On GANs and GMMs](https://mlsanity.com/paper/1805.12462/) (2018)
- [Processing of missing data by neural networks](https://mlsanity.com/paper/1805.07405/) (2018)
- [Flow Models for Arbitrary Conditional Likelihoods](https://mlsanity.com/paper/1909.06319/) (2019)
- [MIDA: Multiple Imputation using Denoising Autoencoders](https://mlsanity.com/paper/1705.02737/) (2017)
- [What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features](https://mlsanity.com/paper/1903.01620/) (2019)
- [Classification with Low Rank and Missing Data](https://mlsanity.com/paper/1501.03273/) (2015)
- [Estimating conditional density of missing values using deep Gaussian mixture model](https://mlsanity.com/paper/2010.02183/) (2020)
- [Processing of incomplete images by (graph) convolutional neural networks](https://mlsanity.com/paper/2010.13914/) (2020)

## Built on by (most cited first, 4 of 4)

- [ReMasker: Imputing Tabular Data with Masked Autoencoding](https://mlsanity.com/paper/2309.13793/) (2023)
- [TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration](https://mlsanity.com/paper/2311.15335/) (2023)
- [FLYNN: Robust Neural Network for Robot Navigation using Fly Brain Topology](https://mlsanity.com/paper/2607.00025/) (2026)
- [Meta-Imputation Balanced (MIB): An Ensemble Approach for Handling Missing Data in Biomedical Machine Learning](https://mlsanity.com/paper/2509.03316/) (2025)

## Abstract (arXiv)

Processing of missing data by modern neural networks, such as CNNs, remains a fundamental, yet unsolved challenge, which naturally arises in many practical applications, like image inpainting or autonomous vehicles and robots. While imputation-based techniques are still one of the most popular solutions, they frequently introduce unreliable information to the data and do not take into account the uncertainty of estimation, which may be destructive for a machine learning model. In this paper, we present MisConv, a general mechanism, for adapting various CNN architectures to process incomplete images. By modeling the distribution of missing values by the Mixture of Factor Analyzers, we cover the spectrum of possible replacements and find an analytical formula for the expected value of convolution operator applied to the incomplete image. The whole framework is realized by matrix operations, which makes MisConv extremely efficient in practice. Experiments performed on various image processing tasks demonstrate that MisConv achieves superior or comparable performance to the state-of-the-art methods.