mlsanityData to 7 Oct 2026

TabDDPM: Modelling Tabular Data with Diffusion Models

arXiv 2209.15421 ↗First posted 30 Sep 2022cs.LGcited by 373

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

Abstract (arXiv)

Denoising diffusion probabilistic models are currently becoming the leading paradigm of generative modeling for many important data modalities. Being the most prevalent in the computer vision community, diffusion models have also recently gained some attention in other domains, including speech, NLP, and graph-like data. In this work, we investigate if the framework of diffusion models can be advantageous for general tabular problems, where datapoints are typically represented by vectors of heterogeneous features. The inherent heterogeneity of tabular data makes it quite challenging for accurate modeling, since the individual features can be of completely different nature, i.e., some of them can be continuous and some of them can be discrete. To address such data types, we introduce TabDDPM -- a diffusion model that can be universally applied to any tabular dataset and handles any type of feature. We extensively evaluate TabDDPM on a wide set of benchmarks and demonstrate its superiority over existing GAN/VAE alternatives, which is consistent with the advantage of diffusion models in other fields. Additionally, we show that TabDDPM is eligible for privacy-oriented setups, where the original datapoints cannot be publicly shared.

Key facts. Cited by 373 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 37 of its 57 references that are in the map. First posted on arXiv 30 Sep 2022.

Builds on

37 of 57 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar
  2. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation7 Jul

Other references · 35

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  9. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  10. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  11. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  12. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
23 more
  1. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  2. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  3. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  4. 2019Modeling Tabular data using Conditional GANcited by 695
  5. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  6. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  7. 2014OpenML: networked science in machine learningcited by 523
  8. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  9. 2022A Continuous Time Framework for Discrete Denoising Modelscited by 437
  10. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  11. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  12. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  13. 2022Torsional Diffusion for Molecular Conformer Generationcited by 262
  14. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  15. 2018Handling Incomplete Heterogeneous Data using VAEscited by 148
  16. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  17. 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
  18. 2020Differentially Private Synthetic Medical Data Generation using Convolutional GANscited by 52
  19. 2022SOS: Score-based Oversampling for Tabular Datacited by 29
  20. 2021OCT-GAN: Neural ODE-based Conditional Tabular GANscited by 27
  21. 2022Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesiscited by 24
  22. 2020Relational Data Synthesis using Generative Adversarial Networks: A Design Space Explorationcited by 21
  23. 2022Generative Trees: Adversarial and Copycatcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 44; 2024: 90; 2025: 113; 2026: 125.

373 papers.

Sort:

By area:

  1. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 294
  2. 2023Self-Consuming Generative Models Go MADcited by 239
  3. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
  4. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  5. 2023Synthetic Experience Replaycited by 100
  6. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 93
  7. 2023On Diffusion Modeling for Anomaly Detectioncited by 71
  8. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 60
  9. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 60
  10. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  11. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  12. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesiscited by 42
38 more
  1. 2023FinDiff: Diffusion Models for Financial Tabular Data Generationcited by 41
  2. 2023Stochastic Segmentation with Conditional Categorical Diffusion Modelscited by 38
  3. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 38
  4. 2023Diffusion Model-Augmented Behavioral Cloningcited by 37
  5. 2023TabMT: Generating tabular data with masked transformerscited by 36
  6. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  7. 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
  8. 2024A Systematic Review on Long-Tailed Learningcited by 27
  9. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  10. 2024TabPFGen -- Tabular Data Generation with TabPFNcited by 26
  11. 2023Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Modelscited by 24
  12. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizingcited by 24
  13. 2023Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmarkcited by 23
  14. 2023A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learningcited by 23
  15. 2024A Survey on Diffusion Models for Recommender Systemscited by 20
  16. 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spacescited by 19
  17. 2024A Survey on Deep Tabular Learningcited by 18
  18. 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintscited by 18
  19. 2023Synthesizing Mixed-type Electronic Health Records using Diffusion Modelscited by 17
  20. 2024Systematic Assessment of Tabular Data Synthesiscited by 17
  21. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 17
  22. 2023DiSK: A Diffusion Model for Structured Knowledgecited by 16
  23. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 16
  24. 2024Differentially Private Tabular Data Synthesis using Large Language Modelscited by 16
  25. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  26. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  27. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generationcited by 15
  28. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 15
  29. 2025Exponential Family Variational Flow Matching for Tabular Data Generationcited by 15
  30. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  31. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  32. 2024EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Modelscited by 14
  33. 2023DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generationcited by 13
  34. 2024CTSyn: A Foundation Model for Cross Tabular Data Generationcited by 13
  35. 2025TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Datacited by 13
  36. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 13
  37. 2023On the Usefulness of Synthetic Tabular Data Generationcited by 12
  38. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 12

50 most cited of 373 All 373 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Tabular GANs for uneven distribution
  2. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model
  3. 2022Diffusion Models in Vision: A Survey
  4. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance
  5. 2022Diffusion models for missing value imputation in tabular data
  6. 2026XGenBoost: Synthesizing Small and Large Tabular Datasets with XGBoost
  7. 2024An overview of diffusion models for generative artificial intelligence
  8. 2024I-Diff: Structural Regularization for High-Fidelity Diffusion Models