# GEDI: A Graph-based End-to-end Data Imputation Framework

arXiv: https://arxiv.org/abs/2208.06573 · HTML: https://mlsanity.com/paper/2208.06573/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 13 Aug 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings](https://mlsanity.com/paper/2006.13009/) (2020)
- [Handling Incomplete Heterogeneous Data using VAEs](https://mlsanity.com/paper/1807.03653/) (2018)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks](https://mlsanity.com/paper/2108.00298/) (2021)
- [VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data](https://mlsanity.com/paper/2006.11941/) (2020)
- [Missing Data Imputation with Adversarially-trained Graph Convolutional Networks](https://mlsanity.com/paper/1905.01907/) (2019)
- [Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs](https://mlsanity.com/paper/2007.08294/) (2020)
- [Processing of missing data by neural networks](https://mlsanity.com/paper/1805.07405/) (2018)
- [Spectral Collaborative Filtering](https://mlsanity.com/paper/1808.10523/) (2018)
- [DAEMA: Denoising Autoencoder with Mask Attention](https://mlsanity.com/paper/2106.16057/) (2021)

## Built on by (most cited first, 5 of 5)

- [Transformed Distribution Matching for Missing Value Imputation](https://mlsanity.com/paper/2302.10363/) (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)
- [Missing Value Imputation for Multi-attribute Sensor Data Streams via Message Propagation (Extended Version)](https://mlsanity.com/paper/2311.07344/) (2023)
- [When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatch](https://mlsanity.com/paper/2610.20342/) (2026)

## Abstract (arXiv)

Data imputation is an effective way to handle missing data, which is common in practical applications. In this study, we propose and test a novel data imputation process that achieve two important goals: (1) preserve the row-wise similarities among observations and column-wise contextual relationships among features in the feature matrix, and (2) tailor the imputation process to specific downstream label prediction task. The proposed imputation process uses Transformer network and graph structure learning to iteratively refine the contextual relationships among features and similarities among observations. Moreover, it uses a meta-learning framework to select features that are influential to the downstream prediction task of interest. We conduct experiments on real-world large data sets, and show that the proposed imputation process consistently improves imputation and label prediction performance over a variety of benchmark methods.