mlsanityData to 14 Oct 2026

Diffusion models for missing value imputation in tabular data

arXiv 2210.17128 ↗First posted 31 Oct 2022cs.LG cs.AIcited by 77

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Missing value imputation in machine learning is the task of estimating the missing values in the dataset accurately using available information. In this task, several deep generative modeling methods have been proposed and demonstrated their usefulness, e.g., generative adversarial imputation networks. Recently, diffusion models have gained popularity because of their effectiveness in the generative modeling task in images, texts, audio, etc. To our knowledge, less attention has been paid to the investigation of the effectiveness of diffusion models for missing value imputation in tabular data. Based on recent development of diffusion models for time-series data imputation, we propose a diffusion model approach called "Conditional Score-based Diffusion Models for Tabular data" (TabCSDI). To effectively handle categorical variables and numerical variables simultaneously, we investigate three techniques: one-hot encoding, analog bits encoding, and feature tokenization. Experimental results on benchmark datasets demonstrated the effectiveness of TabCSDI compared with well-known existing methods, and also emphasized the importance of the categorical embedding techniques.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 13 of its 27 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

13 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar
  2. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul
  3. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting28 Jan

Other references · 10

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  4. 2022Diffusion Models in Vision: A Surveycited by 1,015
  5. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  6. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 373
  7. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  8. 2018Handling Incomplete Heterogeneous Data using VAEscited by 149
  9. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 83
  10. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 27; 2025: 24; 2026: 18.

77 papers.

Sort:

By area:

  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  2. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  3. 2024A Survey on Diffusion Models for Time Series and Spatio-Temporal Datacited by 67
  4. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 63
  5. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 62
  6. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 39
  7. 2022Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Modelcited by 28
  8. 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
  9. 2024TabPFGen -- Tabular Data Generation with TabPFNcited by 28
  10. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
  11. 2024A Survey on Diffusion Models for Recommender Systemscited by 20
  12. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
38 more
  1. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  2. 2023A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Themcited by 15
  3. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generationcited by 15
  4. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  5. 2023Synthetic Health-related Longitudinal Data with Mixed-type Variables Generated using Diffusion Modelscited by 11
  6. 2025TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationcited by 10
  7. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusioncited by 9
  8. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Datacited by 8
  9. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  10. 2023Boosting Data Analytics With Synthetic Volume Expansioncited by 7
  11. 2024Review for Handling Missing Data with special missing mechanismcited by 7
  12. 2024Latent Causal Modeling for 3D Brain MRI Counterfactualscited by 7
  13. 2024Understanding and Mitigating Memorization in Diffusion Models for Tabular Datacited by 7
  14. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Modelcited by 6
  15. 2025Missing Data Imputation by Reducing Mutual Information with Rectified Flowscited by 6
  16. 2024Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Treescited by 5
  17. 2025Diffusion Transformers for Tabular Data Time Series Generationcited by 5
  18. 2026ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimationscited by 5
  19. 2024Unmasking Trees for Tabular Datacited by 4
  20. 2024Preserving logical and functional dependencies in synthetic tabular datacited by 4
  21. 2024Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Datacited by 4
  22. 2025CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputationcited by 4
  23. 2025Ensembling Membership Inference Attacks Against Tabular Generative Modelscited by 4
  24. 2025Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesiscited by 4
  25. 2024In-Database Data Imputationcited by 3
  26. 2024Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flowcited by 3
  27. 2025CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generationcited by 3
  28. 2024Diffusion model for relational inferencecited by 2
  29. 2024White Matter Geometry-Guided Score-Based Diffusion Model for Tissue Microstructure Imputation in Tractography Imagingcited by 2
  30. 2024SketchFill: Sketch-Guided Code Generation for Imputing Derived Missing Valuescited by 2
  31. 2025Impute-MACFM: Imputation based on Mask-Aware Flow Matchingcited by 2
  32. 2025Beyond Accuracy: An Empirical Study of Uncertainty Estimation in Imputationcited by 2
  33. 2026MIDST Challenge at SaTML 2025: Membership Inference over Diffusion-models-based Synthetic Tabular datacited by 2
  34. 2026Missingness-aware Data Imputation via AI-powered Bayesian Generative Modelingcited by 2
  35. 2024Bridging Design Gaps: A Parametric Data Completion Approach With Graph Guided Diffusion Modelscited by 1
  36. 2024Table Transformers for Imputing Textual Attributescited by 1
  37. 2025Enhancing Crash Frequency Modeling Based on Augmented Multi-Type Data by Hybrid VAE-Diffusion-Based Generative Neural Networkscited by 1
  38. 2025DeepIFSAC: Deep Imputation of Missing Values Using Feature and Sample Attention within Contrastive Frameworkcited by 1

50 most cited of 77 All 77 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation
  2. 2025MissDDIM: Deterministic and Efficient Conditional Diffusion for Tabular Data Imputation
  3. 2024MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation
  4. 2023Continuous Diffusion for Mixed-Type Tabular Data
  5. 2025TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
  6. 2026Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
  7. 2022TabDDPM: Modelling Tabular Data with Diffusion Models
  8. 2024Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation