# TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation

arXiv: https://arxiv.org/abs/2410.20626 · HTML: https://mlsanity.com/paper/2410.20626/

## Key facts

- Cited by 63 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 27 of its 34 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Simple and Effective Masked Diffusion Language Models](https://mlsanity.com/paper/2406.07524/) (2024)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Simplified and Generalized Masked Diffusion for Discrete Data](https://mlsanity.com/paper/2406.04329/) (2024)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [Handling Missing Data with Graph Representation Learning](https://mlsanity.com/paper/2010.16418/) (2020)
- [STaSy: Score-based Tabular data Synthesis](https://mlsanity.com/paper/2210.04018/) (2022)
- [Restart Sampling for Improving Generative Processes](https://mlsanity.com/paper/2306.14878/) (2023)
- [CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis](https://mlsanity.com/paper/2304.12654/) (2023)
- [Diffusion models for missing value imputation in tabular data](https://mlsanity.com/paper/2210.17128/) (2022)
- [SOS: Score-based Oversampling for Tabular Data](https://mlsanity.com/paper/2206.08555/) (2022)
- [Continuous Diffusion for Mixed-Type Tabular Data](https://mlsanity.com/paper/2312.10431/) (2023)

## Built on by (most cited first, 30 of 63)

- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [The DCR Delusion: Measuring the Privacy Risk of Synthetic Data](https://mlsanity.com/paper/2505.01524/) (2025)
- [Learning Flexible Forward Trajectories for Masked Molecular Diffusion](https://mlsanity.com/paper/2505.16790/) (2025)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations](https://mlsanity.com/paper/2601.23068/) (2026)
- [Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis](https://mlsanity.com/paper/2503.02152/) (2025)
- [RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models](https://mlsanity.com/paper/2506.00710/) (2025)
- [Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features](https://mlsanity.com/paper/2601.22816/) (2026)
- [Graph-Conditional Flow Matching for Relational Data Generation](https://mlsanity.com/paper/2505.15668/) (2025)
- [CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation](https://mlsanity.com/paper/2506.14206/) (2025)
- [Masked Diffusion Models are Secretly Learned-Order Autoregressive Models](https://mlsanity.com/paper/2511.19152/) (2025)
- [Improving TabPFN's Synthetic Data Generation by Integrating Causal Structure](https://mlsanity.com/paper/2603.10254/) (2026)
- [TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer](https://mlsanity.com/paper/2501.01216/) (2025)
- [Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era](https://mlsanity.com/paper/2508.19570/) (2025)
- [TabSCM: A practical Framework for Generating Realistic Tabular Data](https://mlsanity.com/paper/2604.22337/) (2026)
- [TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data](https://mlsanity.com/paper/2607.03926/) (2026)
- [Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models](https://mlsanity.com/paper/2607.21636/) (2026)
- [A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective](https://mlsanity.com/paper/2505.22322/) (2025)
- [SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis](https://mlsanity.com/paper/2509.22352/) (2025)
- [Causal-Aware Tabular GANs with Reinforcement Learning](https://mlsanity.com/paper/2510.24046/) (2025)
- [Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective](https://mlsanity.com/paper/2601.22434/) (2026)
- [Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation](https://mlsanity.com/paper/2602.04785/) (2026)
- [TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion](https://mlsanity.com/paper/2602.22586/) (2026)
- [A Sobering Look at Tabular Data Generation via Probabilistic Circuits](https://mlsanity.com/paper/2603.23016/) (2026)
- [Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning](https://mlsanity.com/paper/2605.04911/) (2026)
- [Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion](https://mlsanity.com/paper/2605.06261/) (2026)
- [Active Tabular Augmentation via Policy-Guided Diffusion Inpainting](https://mlsanity.com/paper/2605.10315/) (2026)
- [AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking](https://mlsanity.com/paper/2606.03347/) (2026)
- [GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models](https://mlsanity.com/paper/2608.18849/) (2026)
- [Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review](https://mlsanity.com/paper/2504.18544/) (2025)

## Abstract (arXiv)

Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its inherent heterogeneous data types, complex inter-correlations, and intricate column-wise distributions. In this paper, we introduce TabDiff, a joint diffusion framework that models all mixed-type distributions of tabular data in one model. Our key innovation is the development of a joint continuous-time diffusion process for numerical and categorical data, where we propose feature-wise learnable diffusion processes to counter the high disparity of different feature distributions. TabDiff is parameterized by a transformer handling different input types, and the entire framework can be efficiently optimized in an end-to-end fashion. We further introduce a mixed-type stochastic sampler to automatically correct the accumulated decoding error during sampling, and propose classifier-free guidance for conditional missing column value imputation. Comprehensive experiments on seven datasets demonstrate that TabDiff achieves superior average performance over existing competitive baselines across all eight metrics, with up to 22.5% improvement over the state-of-the-art model on pair-wise column correlation estimations. Code is available at https://github.com/MinkaiXu/TabDiff.