# Missing Data Imputation with Adversarially-trained Graph Convolutional Networks

arXiv: https://arxiv.org/abs/1905.01907 · HTML: https://mlsanity.com/paper/1905.01907/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 30 of 54)

- [Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks](https://mlsanity.com/paper/2108.00298/) (2021)
- [Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations](https://mlsanity.com/paper/2205.13479/) (2022)
- [Simplicial Attention Networks](https://mlsanity.com/paper/2204.09455/) (2022)
- [Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging](https://mlsanity.com/paper/2109.12144/) (2021)
- [Generalized Simplicial Attention Neural Networks](https://mlsanity.com/paper/2309.02138/) (2023)
- [Learning Strong Graph Neural Networks with Weak Information](https://mlsanity.com/paper/2305.18457/) (2023)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Simplicial Attention Neural Networks](https://mlsanity.com/paper/2203.07485/) (2022)
- [Data Imputation with Iterative Graph Reconstruction](https://mlsanity.com/paper/2212.02810/) (2022)
- [Towards Data-centric Graph Machine Learning: Review and Outlook](https://mlsanity.com/paper/2309.10979/) (2023)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)
- [On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing](https://mlsanity.com/paper/2501.02191/) (2025)
- [Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns](https://mlsanity.com/paper/2109.08357/) (2021)
- [Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks](https://mlsanity.com/paper/2211.11596/) (2022)
- [DAEMA: Denoising Autoencoder with Mask Attention](https://mlsanity.com/paper/2106.16057/) (2021)
- [EGG-GAE: scalable graph neural networks for tabular data imputation](https://mlsanity.com/paper/2210.10446/) (2022)
- [Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation (Extended Version)](https://mlsanity.com/paper/2311.07344/) (2023)
- [LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models](https://mlsanity.com/paper/2404.01165/) (2024)
- [Siamese Attribute-missing Graph Auto-encoder](https://mlsanity.com/paper/2112.04842/) (2021)
- [Revisiting Initializing Then Refining: An Incomplete and Missing Graph Imputation Network](https://mlsanity.com/paper/2302.07524/) (2023)
- [Graph Neural Networks: a bibliometrics overview](https://mlsanity.com/paper/2201.01188/) (2022)
- [Differentiable and Scalable Generative Adversarial Models for Data Imputation](https://mlsanity.com/paper/2201.03202/) (2022)
- [GEDI: A Graph-based End-to-end Data Imputation Framework](https://mlsanity.com/paper/2208.06573/) (2022)
- [Correlation visualization under missing values: a comparison between imputation and direct parameter estimation methods](https://mlsanity.com/paper/2305.06044/) (2023)
- [Recovering Missing Node Features with Local Structure-based Embeddings](https://mlsanity.com/paper/2309.09068/) (2023)
- [Explainability of Machine Learning Models under Missing Data](https://mlsanity.com/paper/2407.00411/) (2024)
- [AmGCL: Feature Imputation of Attribute Missing Graph via Self-supervised Contrastive Learning](https://mlsanity.com/paper/2305.03741/) (2023)
- [Wasserstein Graph Neural Networks for Graphs with Missing Attributes](https://mlsanity.com/paper/2102.03450/) (2021)
- [Impact Of Missing Data Imputation On The Fairness And Accuracy Of Graph Node Classifiers](https://mlsanity.com/paper/2211.00783/) (2022)
- [Multi-scale Temporal Fusion Transformer for Incomplete Vehicle Trajectory Prediction](https://mlsanity.com/paper/2409.00904/) (2024)

## Abstract (arXiv)

Missing data imputation (MDI) is a fundamental problem in many scientific disciplines. Popular methods for MDI use global statistics computed from the entire data set (e.g., the feature-wise medians), or build predictive models operating independently on every instance. In this paper we propose a more general framework for MDI, leveraging recent work in the field of graph neural networks (GNNs). We formulate the MDI task in terms of a graph denoising autoencoder, where each edge of the graph encodes the similarity between two patterns. A GNN encoder learns to build intermediate representations for each example by interleaving classical projection layers and locally combining information between neighbors, while another decoding GNN learns to reconstruct the full imputed data set from this intermediate embedding. In order to speed-up training and improve the performance, we use a combination of multiple losses, including an adversarial loss implemented with the Wasserstein metric and a gradient penalty. We also explore a few extensions to the basic architecture involving the use of residual connections between layers, and of global statistics computed from the data set to improve the accuracy. On a large experimental evaluation, we show that our method robustly outperforms state-of-the-art approaches for MDI, especially for large percentages of missing values.