# FragmGAN: Generative Adversarial Nets for Fragmentary Data Imputation and Prediction

arXiv: https://arxiv.org/abs/2203.04692 · HTML: https://mlsanity.com/paper/2203.04692/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 9 Mar 2022.

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

- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [Variational Autoencoder with Arbitrary Conditioning](https://mlsanity.com/paper/1806.02382/) (2018)
- [not-MIWAE: Deep Generative Modelling with Missing not at Random Data](https://mlsanity.com/paper/2006.12871/) (2020)
- [MCFlow: Monte Carlo Flow Models for Data Imputation](https://mlsanity.com/paper/2003.12628/) (2020)
- [CollaGAN : Collaborative GAN for Missing Image Data Imputation](https://mlsanity.com/paper/1901.09764/) (2019)
- [Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption](https://mlsanity.com/paper/1910.12774/) (2019)
- [MIDA: Multiple Imputation using Denoising Autoencoders](https://mlsanity.com/paper/1705.02737/) (2017)
- [Improving Missing Data Imputation with Deep Generative Models](https://mlsanity.com/paper/1902.10666/) (2019)
- [PC-GAIN: Pseudo-label Conditional Generative Adversarial Imputation Networks for Incomplete Data](https://mlsanity.com/paper/2011.07770/) (2020)
- [Integrating multi-source block-wise missing data in model selection](https://mlsanity.com/paper/1901.03797/) (2019)
- [Integrative Factor Regression and Its Inference for Multimodal Data Analysis](https://mlsanity.com/paper/1911.04056/) (2019)
- [HexaGAN: Generative Adversarial Nets for Real World Classification](https://mlsanity.com/paper/1902.09913/) (2019)
- [Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data](https://mlsanity.com/paper/2102.12679/) (2021)
- [Missing Features Reconstruction Using a Wasserstein Generative Adversarial Imputation Network](https://mlsanity.com/paper/2006.11783/) (2020)
- [Imputation of Missing Data with Class Imbalance using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2012.00220/) (2020)
- [Unsupervised Data Imputation via Variational Inference of Deep Subspaces](https://mlsanity.com/paper/1903.03503/) (2019)
- [IFGAN: Missing Value Imputation using Feature-specific Generative Adversarial Networks](https://mlsanity.com/paper/2012.12581/) (2020)

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

- [Transformed Distribution Matching for Missing Value Imputation](https://mlsanity.com/paper/2302.10363/) (2023)
- [Optimal Transport for Structure Learning Under Missing Data](https://mlsanity.com/paper/2402.15255/) (2024)
- [A Context-Aware Approach for Enhancing Data Imputation with Pre-trained Language Models](https://mlsanity.com/paper/2405.17712/) (2024)
- [ClueGAIN: Application of Transfer Learning On Generative Adversarial Imputation Nets (GAIN)](https://mlsanity.com/paper/2302.03140/) (2023)

## Abstract (arXiv)

Modern scientific research and applications very often encounter "fragmentary data" which brings big challenges to imputation and prediction. By leveraging the structure of response patterns, we propose a unified and flexible framework based on Generative Adversarial Nets (GAN) to deal with fragmentary data imputation and label prediction at the same time. Unlike most of the other generative model based imputation methods that either have no theoretical guarantee or only consider Missing Completed At Random (MCAR), the proposed FragmGAN has theoretical guarantees for imputation with data Missing At Random (MAR) while no hint mechanism is needed. FragmGAN trains a predictor with the generator and discriminator simultaneously. This linkage mechanism shows significant advantages for predictive performances in extensive experiments.