mlsanityData to 14 Oct 2026

Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees

arXiv 2309.09968 ↗First posted 18 Sep 2023cs.LGcited by 62

Not on the map. Why?

Cited by 28 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Tabular data is hard to acquire and is subject to missing values. This paper introduces a novel approach for generating and imputing mixed-type (continuous and categorical) tabular data utilizing score-based diffusion and conditional flow matching. In contrast to prior methods that rely on neural networks to learn the score function or the vector field, we adopt XGBoost, a widely used Gradient-Boosted Tree (GBT) technique. To test our method, we build one of the most extensive benchmarks for tabular data generation and imputation, containing 27 diverse datasets and 9 metrics. Through empirical evaluation across the benchmark, we demonstrate that our approach outperforms deep-learning generation methods in data generation tasks and remains competitive in data imputation. Notably, it can be trained in parallel using CPUs without requiring a GPU. Our Python and R code is available at https://github.com/SamsungSAILMontreal/ForestDiffusion.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Builds on 51 of its 147 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

51 of 147 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2022Classifier-Free Diffusion Guidancecited by 5,847
  8. 2022Flow Matching for Generative Modelingcited by 5,702
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  10. 2018Neural Ordinary Differential Equationscited by 3,779
  11. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
38 more
  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  8. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  9. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  10. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  11. 2019Modeling Tabular data using Conditional GANcited by 699
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  13. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  14. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  15. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
  16. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  17. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  18. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  19. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  20. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  21. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  22. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  23. 2022Language Models are Realistic Tabular Data Generatorscited by 294
  24. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 270
  25. 2022On Neural Differential Equationscited by 268
  26. 2018Stochastic Video Generation with a Learned Priorcited by 245
  27. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  28. 2020Stochastic Latent Residual Video Predictioncited by 108
  29. 2014Matrix Completion and Low-Rank SVD via Fast Alternating Least Squarescited by 104
  30. 2019Improved Conditional VRNNs for Video Predictioncited by 104
  31. 2020Missing Data Imputation using Optimal Transportcited by 100
  32. 2019Learning with minibatch Wasserstein : asymptotic and gradient propertiescited by 87
  33. 2022STaSy: Score-based Tabular data Synthesiscited by 86
  34. 2022Diffusion models for missing value imputation in tabular datacited by 77
  35. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  36. 2021Minibatch optimal transport distances; analysis and applicationscited by 65
  37. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 39
  38. 2021Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparisoncited by 7

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 22; 2025: 20; 2026: 19.

62 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  2. 2024A Comprehensive Survey on Data Augmentationcited by 40
  3. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
  4. 2025Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Modelscited by 24
  5. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 19
  6. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 17
  7. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  8. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  9. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 15
  10. 2025Exponential Family Variational Flow Matching for Tabular Data Generationcited by 15
  11. 2025TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Datacited by 14
  12. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 8
38 more
  1. 2024Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Classcited by 8
  2. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  3. 2024Explicit Flow Matching: On The Theory of Flow Matching Algorithms with Applicationscited by 6
  4. 2024Tabular Data Synthesis with Differential Privacy: A Surveycited by 6
  5. 2025Flow Matching for Tabular Data Synthesiscited by 6
  6. 2024Do we need rebalancing strategies? A theoretical and empirical study around SMOTE and its variantscited by 5
  7. 2024Guided Discrete Diffusion for Electronic Health Record Generationcited by 5
  8. 2024Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Treescited by 5
  9. 2024Scaling Up Diffusion and Flow-based XGBoost Modelscited by 5
  10. 2025TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representationcited by 5
  11. 2025CFMI: Flow Matching for Missing Data Imputationcited by 5
  12. 2024Unmasking Trees for Tabular Datacited by 4
  13. 2024A text-to-tabular approach to generate synthetic patient data using LLMscited by 4
  14. 2025Tabby: A Language Model Architecture for Tabular and Structured Data Synthesiscited by 4
  15. 2025One Pipeline, Many Transformers: Pattern-Specific Imputation Specialists for Tabular Missing Datacited by 4
  16. 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Featurescited by 4
  17. 2024BUFF: Boosted Decision Tree based Ultra-Fast Flow matchingcited by 3
  18. 2024Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysiscited by 3
  19. 2025Graph-Conditional Flow Matching for Relational Data Generationcited by 3
  20. 2024A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approachescited by 2
  21. 2024Diffusion Boosted Treescited by 2
  22. 2025TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformercited by 2
  23. 2025Generative Unordered Flow for Set-Structured Data Generationcited by 2
  24. 2025Diffusion Models with Double Guidance: Generate with aggregated datasetscited by 2
  25. 2026CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Datacited by 2
  26. 2026Missingness-aware Data Imputation via AI-powered Bayesian Generative Modelingcited by 2
  27. 2024Table Transformers for Imputing Textual Attributescited by 1
  28. 2024NRGBoost: Energy-Based Generative Boosted Treescited by 1
  29. 2024Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matchingcited by 1
  30. 2025Interleaved Gibbs Diffusion: Generating Discrete-Continuous Data with Implicit Constraintscited by 1
  31. 2026When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Modelscited by 1
  32. 2026AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Maskingcited by 1
  33. 2026Towards More General Control of Diffusion Models Using Jeffrey Guidancecited by 1
  34. 2025IMAGIC-500: IMputation benchmark on A Generative Imaginary Country (500k samples)cited by 0
  35. 2025Privacy-Preserving Tabular Synthetic Data Generation Using TabularARGNcited by 0
  36. 2025An Interdisciplinary and Cross-Task Review on Missing Data Imputationcited by 0
  37. 2025Boosting Predictive Performance on Tabular Data through Data Augmentation with Latent-Space Flow-Based Diffusioncited by 0
  38. 2026Nearly Optimal Bayesian Inference for Structural Missingnesscited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
  2. 2026XGenBoost: Synthesizing Small and Large Tabular Datasets with XGBoost
  3. 2024Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flow
  4. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
  5. 2026TabGift: A Context-Efficient Foundation Model for Tabular Data Generation
  6. 2025MissHDD: Hybrid Deterministic Diffusion for Hetrogeneous Incomplete Data Imputation
  7. 2026Generating Benchmark Health Data Using a Tabular Diffusion Transformer
  8. 2024DiffImpute: Tabular Data Imputation With Denoising Diffusion Probabilistic Model