# Processing of missing data by neural networks

arXiv: https://arxiv.org/abs/1805.07405 · HTML: https://mlsanity.com/paper/1805.07405/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2018.

## Built on by (most cited first, 30 of 37)

- [Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging](https://mlsanity.com/paper/2109.12144/) (2021)
- [Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo](https://mlsanity.com/paper/2202.04599/) (2022)
- [Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference](https://mlsanity.com/paper/2109.09506/) (2021)
- [Missing Value Estimation using Clustering and Deep Learning within Multiple Imputation Framework](https://mlsanity.com/paper/2202.13734/) (2022)
- [Active Visual Exploration Based on Attention-Map Entropy](https://mlsanity.com/paper/2303.06457/) (2023)
- [EGG-GAE: scalable graph neural networks for tabular data imputation](https://mlsanity.com/paper/2210.10446/) (2022)
- [LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models](https://mlsanity.com/paper/2404.01165/) (2024)
- [AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale](https://mlsanity.com/paper/2404.03482/) (2024)
- [Review for Handling Missing Data with special missing mechanism](https://mlsanity.com/paper/2404.04905/) (2024)
- [Economic Nowcasting with Long Short-Term Memory Artificial Neural Networks (LSTM)](https://mlsanity.com/paper/2106.08901/) (2021)
- [GEDI: A Graph-based End-to-end Data Imputation Framework](https://mlsanity.com/paper/2208.06573/) (2022)
- [Robust Simulation-Based Inference under Missing Data via Neural Processes](https://mlsanity.com/paper/2503.01287/) (2025)
- [MisConv: Convolutional Neural Networks for Missing Data](https://mlsanity.com/paper/2110.14010/) (2021)
- [Modeling Continuous Time Sequences with Intermittent Observations using Marked Temporal Point Processes](https://mlsanity.com/paper/2206.12414/) (2022)
- [Deep learning with missing data](https://mlsanity.com/paper/2504.15388/) (2025)
- [Probing the Effect of Selection Bias on Generalization: A Thought Experiment](https://mlsanity.com/paper/2105.09934/) (2021)
- [Forecasting Loss of Signal in Optical Networks with Machine Learning](https://mlsanity.com/paper/2201.07089/) (2022)
- [No imputation without representation](https://mlsanity.com/paper/2206.14254/) (2022)
- [Irregularly-Sampled Time Series Modeling with Spline Networks](https://mlsanity.com/paper/2210.10630/) (2022)
- [Training of Neural Networks with Uncertain Data: A Mixture of Experts Approach](https://mlsanity.com/paper/2312.08083/) (2023)
- [SEMF: Supervised Expectation-Maximization Framework for Predicting Intervals](https://mlsanity.com/paper/2405.18176/) (2024)
- [HI-PMK: A Data-Dependent Kernel for Incomplete Heterogeneous Data Representation](https://mlsanity.com/paper/2501.04300/) (2025)
- [MAIN: Multihead-Attention Imputation Networks](https://mlsanity.com/paper/2102.05428/) (2021)
- [PROMISSING: Pruning Missing Values in Neural Networks](https://mlsanity.com/paper/2206.01640/) (2022)
- [Towards Better Modeling with Missing Data: A Contrastive Learning-based Visual Analytics Perspective](https://mlsanity.com/paper/2309.09744/) (2023)
- [Data Imputation by Pursuing Better Classification: A Supervised Kernel-Based Method](https://mlsanity.com/paper/2405.07800/) (2024)
- [Ordinal-Quadruplet: Retrieval of Missing Classes in Ordinal Time Series](https://mlsanity.com/paper/2201.09907/) (2022)
- [Radial Spike and Slab Bayesian Neural Networks for Sparse Data in Ransomware Attacks](https://mlsanity.com/paper/2205.14759/) (2022)
- [Regression with Sensor Data Containing Incomplete Observations](https://mlsanity.com/paper/2304.13415/) (2023)
- [Enhancing Missing Data Imputation through Combined Bipartite Graph and Complete Directed Graph](https://mlsanity.com/paper/2411.04907/) (2024)

## Abstract (arXiv)

We propose a general, theoretically justified mechanism for processing missing data by neural networks. Our idea is to replace typical neuron's response in the first hidden layer by its expected value. This approach can be applied for various types of networks at minimal cost in their modification. Moreover, in contrast to recent approaches, it does not require complete data for training. Experimental results performed on different types of architectures show that our method gives better results than typical imputation strategies and other methods dedicated for incomplete data.