mlsanityData to 7 Oct 2026

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

arXiv 2310.09656 ↗First posted 14 Oct 2023cs.LGcited by 183

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

also in 1 more
Abstract (arXiv)

Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions and a blend of data types of tabular data. This paper introduces Tabsyn, a methodology that synthesizes tabular data by leveraging a diffusion model within a variational autoencoder (VAE) crafted latent space. The key advantages of the proposed Tabsyn include (1) Generality: the ability to handle a broad spectrum of data types by converting them into a single unified space and explicitly capture inter-column relations; (2) Quality: optimizing the distribution of latent embeddings to enhance the subsequent training of diffusion models, which helps generate high-quality synthetic data, (3) Speed: much fewer number of reverse steps and faster synthesis speed than existing diffusion-based methods. Extensive experiments on six datasets with five metrics demonstrate that Tabsyn outperforms existing methods. Specifically, it reduces the error rates by 86% and 67% for column-wise distribution and pair-wise column correlation estimations compared with the most competitive baselines.

Key facts. Cited by 183 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 27 of its 38 references that are in the map. First posted on arXiv 14 Oct 2023.

Builds on

27 of 38 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis25 Apr
  2. 2022Diffusion models for missing value imputation in tabular data31 Oct
  3. 2022STaSy: Score-based Tabular data Synthesis8 Oct
  4. 2022TabDDPM: Modelling Tabular Data with Diffusion Models30 Sep

Other references · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2016Layer Normalizationcited by 5,579
  7. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  8. 2017Neural Discrete Representation Learningcited by 4,650
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  12. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
11 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  2. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  3. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  4. 2019Modeling Tabular data using Conditional GANcited by 695
  5. 2021Score-based Generative Modeling in Latent Spacecited by 634
  6. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  7. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  8. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  9. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  10. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 85
  11. 2022SOS: Score-based Oversampling for Tabular Datacited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 41; 2025: 75; 2026: 62.

183 papers.

Sort:

By area:

  1. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  2. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 60
  3. 2024Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connectionscited by 47
  4. 2024A Geometric Framework for Understanding Memorization in Generative Modelscited by 40
  5. 2025Efficient Diffusion Models: A Surveycited by 35
  6. 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
  7. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  8. 2024A Survey on Diffusion Models for Recommender Systemscited by 20
  9. 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spacescited by 19
  10. 2024Systematic Assessment of Tabular Data Synthesiscited by 17
  11. 2024DiffPuter: Empowering Diffusion Models for Missing Data Imputationcited by 17
  12. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 16
38 more
  1. 2024HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protectioncited by 16
  2. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generationcited by 15
  3. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 15
  4. 2025Exponential Family Variational Flow Matching for Tabular Data Generationcited by 15
  5. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 15
  6. 2023The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasetscited by 14
  7. 2024CTSyn: A Foundation Model for Cross Tabular Data Generationcited by 13
  8. 2025TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Datacited by 13
  9. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 13
  10. 2024Balanced Mixed-Type Tabular Data Synthesis with Diffusion Modelscited by 12
  11. 2024Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Modelscited by 12
  12. 2025The DCR Delusion: Measuring the Privacy Risk of Synthetic Datacited by 11
  13. 2024TimeLDM: Latent Diffusion Model for Unconditional Time Series Generationcited by 10
  14. 2024Privacy Vulnerabilities in Marginals-based Synthetic Datacited by 10
  15. 2025TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationcited by 10
  16. 2025Winning the MIDST Challenge: New Membership Inference Attacks on Diffusion Models for Tabular Data Synthesiscited by 10
  17. 2024Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)cited by 9
  18. 2024DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detectorcited by 9
  19. 2024DiffLM: Controllable Synthetic Data Generation via Diffusion Language Modelscited by 9
  20. 2025Vision-Enhanced Time Series Forecasting via Latent Diffusion Modelscited by 9
  21. 2026Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPOcited by 9
  22. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  23. 2024TABCF: Counterfactual Explanations for Tabular Data Using a Transformer-Based VAEcited by 8
  24. 2024TextSSR: Diffusion-based Data Synthesis for Scene Text Recognitioncited by 8
  25. 2024Synthetic Tabular Data Generation for Imbalanced Classification: The Surprising Effectiveness of an Overlap Classcited by 8
  26. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  27. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusioncited by 8
  28. 2025Joint Relational Database Generation via Graph-Conditional Diffusion Modelscited by 8
  29. 2025Synthetic Tabular Data: Methods, Attacks and Defensescited by 8
  30. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  31. 2025Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphscited by 8
  32. 2023Boosting Data Analytics With Synthetic Volume Expansioncited by 7
  33. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 7
  34. 2024MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Datacited by 7
  35. 2024LaTable: Towards Large Tabular Modelscited by 7
  36. 2024Understanding and Mitigating Memorization in Diffusion Models for Tabular Datacited by 7
  37. 2025Synthetic Data Privacy Metricscited by 7
  38. 2025Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Modelscited by 7

50 most cited of 183 All 183 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizing
  2. 2020Tabular GANs for uneven distribution
  3. 2026XGenBoost: Synthesizing Small and Large Tabular Datasets with XGBoost
  4. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Values
  5. 2026Tabular Foundation Model for Generative Modelling
  6. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Data
  7. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
  8. 2026TabPFN-3.5: Technical Report