mlsanityData to 14 Oct 2026

GAIN: Missing Data Imputation using Generative Adversarial Nets

arXiv 1806.02920 ↗First posted 7 Jun 2018cs.LG stat.MLcited by 352

Not on the map. Why?

Cited by 36 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a novel method for imputing missing data by adapting the well-known Generative Adversarial Nets (GAN) framework. Accordingly, we call our method Generative Adversarial Imputation Nets (GAIN). The generator (G) observes some components of a real data vector, imputes the missing components conditioned on what is actually observed, and outputs a completed vector. The discriminator (D) then takes a completed vector and attempts to determine which components were actually observed and which were imputed. To ensure that D forces G to learn the desired distribution, we provide D with some additional information in the form of a hint vector. The hint reveals to D partial information about the missingness of the original sample, which is used by D to focus its attention on the imputation quality of particular components. This hint ensures that G does in fact learn to generate according to the true data distribution. We tested our method on various datasets and found that GAIN significantly outperforms state-of-the-art imputation methods.

Key facts. Cited by 352 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 55; 2022: 42; 2023: 55; 2024: 77; 2025: 64; 2026: 59.

352 papers.

Sort:

By area:

  1. 2022SAITS: Self-Attention-based Imputation for Time Seriescited by 169
  2. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  3. 2022A Consistent and Efficient Evaluation Strategy for Attribution Methodscited by 102
  4. 2021Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networkscited by 95
  5. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  6. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  7. 2022Diffusion models for missing value imputation in tabular datacited by 77
  8. 2022Learning to Induce Causal Structurecited by 68
  9. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 66
  10. 2022Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observationscited by 64
  11. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 63
  12. 2021What's a good imputation to predict with missing values?cited by 62
38 more
  1. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 62
  2. 2023Generative Table Pre-training Empowers Models for Tabular Predictioncited by 55
  3. 2022Transfer Learning with Deep Tabular Modelscited by 52
  4. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 51
  5. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  6. 2021Generating Synthetic Mixed-type Longitudinal Electronic Health Records for Artificial Intelligent Applicationscited by 47
  7. 2023Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Predictioncited by 47
  8. 2023CUTS+: High-dimensional Causal Discovery from Irregular Time-seriescited by 41
  9. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 39
  10. 2023ReMasker: Imputing Tabular Data with Masked Autoencodingcited by 37
  11. 2023GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputationcited by 35
  12. 2023Large Language Models as Data Preprocessorscited by 34
  13. 2023Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoderscited by 32
  14. 2024TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Datacited by 32
  15. 2023Transformed Distribution Matching for Missing Value Imputationcited by 31
  16. 2021Identifiable Generative Models for Missing Not at Random Data Imputationcited by 30
  17. 2021Spatial Aggregation and Temporal Convolution Networks for Real-time Krigingcited by 27
  18. 2023Graph Deep Learning for Time Series Forecastingcited by 26
  19. 2021NRTSI: Non-Recurrent Time Series Imputationcited by 25
  20. 2024LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationcited by 25
  21. 2021Assessing Fairness in the Presence of Missing Datacited by 24
  22. 2023Learning from data with structured missingnesscited by 24
  23. 2025LSM-2: Learning from Incomplete Wearable Sensor Datacited by 23
  24. 2021Arbitrary Conditional Distributions with Energycited by 22
  25. 2022MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Modelscited by 22
  26. 2022Classification of datasets with imputed missing values: does imputation quality matter?cited by 22
  27. 2023Jellyfish: A Large Language Model for Data Preprocessingcited by 20
  28. 2024GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missingcited by 20
  29. 2021Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Featurescited by 19
  30. 2022The Missing Indicator Method: From Low to High Dimensionscited by 19
  31. 2024Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sportscited by 19
  32. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
  33. 2022Maximizing information from chemical engineering data sets: Applications to machine learningcited by 17
  34. 2021Deconvolutional Networks on Graph Datacited by 16
  35. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  36. 2021Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problemscited by 15
  37. 2022Data Imputation with Iterative Graph Reconstructioncited by 15
  38. 2023A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Themcited by 15

50 most cited of 352 All 352 (JSON)