TabDDPM: Modelling Tabular Data with Diffusion Models

Authors: Akim Kotelnikov, Dmitry Baranchuk, Ivan Rubachev, Artem Babenko

Proceedings of the 40 th International Conference on Machine Learning, Honolulu, Hawaii, USA. PMLR 202, 2023
Submitted to arXiv on 30 Sep. 2022
Abstract

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.

The papers around it, by date and closeness

Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper

How to read this map? Illustrated guide

Closest papers Prior work it builds on Papers that cite it

Papers around this one

Ranked by how close their title and abstract are to this paper’s. Select some to read them together.

Closest papers

  1. Very close Cites this paper Uses this paper in depth
    Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
    Umang Dobhal, Christina Garcia, Sozo Inoue · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet
    Abstract

    Diffusion models are increasingly being utilised to create synthetic tabular and time series data for privacy-preserving augmentation. Tabular Denoising Diffusion Probabilistic Models (TabDDPM) generate high-quality synthetic data from heterogeneous tabular datasets but assume independence between samples, limiting their applicability to time-series domains where temporal dependencies are critical. To address this, we propose a temporal extension of TabDDPM, introducing sequence awareness through the use of lightweight temporal adapters and context-aware embedding modules. By reformulating sensor data into windowed sequences and explicitly modeling temporal context via timestep embeddings, c…

  2. Very close
    DPT-DDPM: A Denoising Diffusion Probabilistic Model for Tabular Data With Differential Privacy Enhancement
    Wei-Jie Niu, Shiyu Ran, A. Celdrán et al. · 2025 · BigData Congress [Services Society] · cited 1 time · Not summarized yet
    Abstract

    The generation of synthetic tabular data is a critical technique for enabling data-driven research while mitigating privacy risks. While Denoising Diffusion Probabilistic Models (DDPMs) have demonstrated superior performance in generating high-fidelity tabular data, they inherently lack mechanisms for strong privacy preservation. To address this limitation, we introduce DPT-DDPM, a novel framework that enhances tabular DDPMs with a practical privacy-enhancing methodology. Our approach incorporates Differentially-Private Stochastic Gradient Descent (DP-SGD) within a novel two-phase continuous training scheme designed to first maximize data utility before enforcing privacy constraints in a sec…

  3. Very close
    TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
    Jacob Si, Zijing Ou, Mike Qu et al. · 2025 · Trans. Mach. Learn. Res. · cited 10 times · Not summarized yet
    Abstract

    Diffusion models have been the predominant generative model for tabular data generation. However, they face the conundrum of modeling under a separate versus a unified data representation. The former encounters the challenge of jointly modeling all multi-modal distributions of tabular data in one model. While the latter alleviates this by learning a single representation for all features, it currently leverages sparse suboptimal encoding heuristics and necessitates additional computation costs. In this work, we address the latter by presenting TabRep, a tabular diffusion architecture trained with a unified continuous representation. To motivate the design of our representation, we provide ge…

  4. Very close
    Diffusion and Flow Matching Models for Tabular Data: A Survey
    Zhong Li, Qi Huang, Lin-Cen Yang et al. · 2025 · cited 14 times · Not summarized yet
    Abstract

    Deep generative models have made rapid progress in image, text, audio, and video generation, and are increasingly being applied to structured records. For tabular data, however, generative modeling remains difficult: a dataset may contain numerical and categorical attributes, missing values, sensitive fields, imbalanced categories, complex feature dependencies, and domain constraints. Earlier tabular data modeling methods based on GANs or VAEs have achieved useful results, but they can suffer from unstable training, mode collapse, weak modeling of multimodal distributions, and fragile handling of mixed-type features. Diffusion models have therefore attracted growing interest because their no…

  5. Very close
    Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
    Mario Villaizán-Vallelado, Matteo Salvatori, Carlos Segura et al. · 2024 · ACM Transactions on Knowledge Discovery from Data · cited 46 times · Not summarized yet
    Abstract

    Data imputation and data generation have important applications across many domains where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emerged as powerful generative models capable of capturing complex data distributions across various data modalities such as image, audio, and time series. Recently, they have been also adapted to generate tabular data. In this article, we propose a diffusion model for tabular data that introduces three key enhancements: (1) a conditioning attention mechanism, (2) an encoder–decoder transformer as the denoising network, and (3) dynamic masking. The conditioning attention mechanism is designed to improve th…

  6. Very close
    Research on Denoising Diffusion Probabilistic Models
    Yi-Yang Jiang · 2024 · Highlights in Science Engineering and Technology · cited 5 times · Not summarized yet
    Abstract

    Diffusion models represent the latest state-of-the-art in the domain of deep generative models, boasting remarkable performance across a broad spectrum of applications. Despite the widespread success of diffusion models in various tasks, the original formulations of these models exhibit notable limitations. The article uses DDPM as an example, thoroughly and deeply exploring and deriving the mathematical principles of the model from two different perspectives. Additionally, this article explores the relationship between diffusion models and five other types of generative models: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), Autoregressive models, Normalizing flows,…

  7. Very close
    Tabular GANs for uneven distribution
    Insaf Ashrapov · 2020 · Not summarized yet
    Abstract

    Generative models for tabular data have evolved rapidly beyond Generative Adversarial Networks (GANs). While GANs pioneered synthetic tabular data generation, recent advances in diffusion models and large language models (LLMs) have opened new paradigms with complementary strengths in sample quality, privacy, and controllability. In this paper, we survey the landscape of tabular data generation across three major paradigms - GANs, diffusion models, and LLMs - and introduce a unified, modular framework that supports all three. The framework encompasses data preprocessing, a model-agnostic interface layer, standardized training and inference pipelines, and a comprehensive evaluation module. We…

  8. Very close Cites this paper Uses this paper in depth
    TabDLM: Free-Form Tabular Data Generation via Joint Numerical-Language Diffusion
    Dong-Hong Cai, Jia-Rui Feng, Yan-Bo Wang et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 1 time · Not summarized yet
    Abstract

    Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or clinical notes) alongside structured numerical and categorical attributes. Generating such heterogeneous tables with joint modeling of different modalities remains challenging. Existing approaches broadly fall into two categories: diffusion-based methods and LLM-based methods. Diffusion models can capture complex dependencies over numerical and categorical features in continuous or discrete spaces, but extending them to open-ended text is nontrivial and o…

Prior work it builds on

  1. Close Used in depth by this paper A method it uses
    Structured Denoising Diffusion Models in Discrete State-Spaces
    Jacob Austin, Daniel D. Johnson, Jonathan Ho et al. · 2021 · Neural Information Processing Systems · cited 2,423 times · Not summarized yet
    Abstract

    Denoising diffusion probabilistic models (DDPMs) (Ho et al. 2020) have shown impressive results on image and waveform generation in continuous state spaces. Here, we introduce Discrete Denoising Diffusion Probabilistic Models (D3PMs), diffusion-like generative models for discrete data that generalize the multinomial diffusion model of Hoogeboom et al. 2021, by going beyond corruption processes with uniform transition probabilities. This includes corruption with transition matrices that mimic Gaussian kernels in continuous space, matrices based on nearest neighbors in embedding space, and matrices that introduce absorbing states. The third allows us to draw a connection between diffusion mode…

  2. Close Used in depth by this paper A method it uses
    Modeling Tabular data using Conditional GAN
    Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante et al. · 2019 · Machine Learning · cited 2,333 times · AI summary available
    Abstract

    Modeling the probability distribution of rows in tabular data and generating realistic synthetic data is a non-trivial task. Tabular data usually contains a mix of discrete and continuous columns. Continuous columns may have multiple modes whereas discrete columns are sometimes imbalanced making the modeling difficult. Existing statistical and deep neural network models fail to properly model this type of data. We design TGAN, which uses a conditional generative adversarial network to address these challenges. To aid in a fair and thorough comparison, we design a benchmark with 7 simulated and 8 real datasets and several Bayesian network baselines. TGAN outperforms Bayesian methods on most o…

  3. Close Used in depth by this paper A method it uses
    Revisiting Deep Learning Models for Tabular Data
    Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov et al. · 2021 · Machine Learning · cited 2,007 times · Not summarized yet
    Abstract

    The necessity of deep learning for tabular data is still an unanswered question addressed by a large number of research efforts. The recent literature on tabular DL proposes several deep architectures reported to be superior to traditional "shallow" models like Gradient Boosted Decision Trees. However, since existing works often use different benchmarks and tuning protocols, it is unclear if the proposed models universally outperform GBDT. Moreover, the models are often not compared to each other, therefore, it is challenging to identify the best deep model for practitioners. In this work, we start from a thorough review of the main families of DL models recently developed for tabular data. …

  4. Close Used in depth by this paper A method it uses
    CTAB-GAN: Effective Table Data Synthesizing
    Zilong Zhao, A. Kunar, H. Van der Scheer et al. · 2021 · Asian Conference on Machine Learning · cited 358 times · Not summarized yet
    Abstract

    While data sharing is crucial for knowledge development, privacy concerns and strict regulation (e.g., European General Data Protection Regulation (GDPR)) unfortunately limit its full effectiveness. Synthetic tabular data emerges as an alternative to enable data sharing while fulfilling regulatory and privacy constraints. The state-of-the-art tabular data synthesizers draw methodologies from generative Adversarial Networks (GAN) and address two main data types in the industry, i.e., continuous and categorical. In this paper, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types, including a mix of continuous and categorical variables. M…

  5. Related Used in depth by this paper A method it uses
    Denoising Diffusion Probabilistic Models
    Jonathan Ho, Ajay Jain, Pieter Abbeel · 2020 · Machine Learning · cited 37,491 times · AI summary available
    Abstract

    We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar…

Papers that cite it

  1. Close Uses this paper in depth
    Geometry-Aware Tabular Diffusion
    David Zagardo · 2026 · arXiv.org · preprint, not peer reviewed · Not summarized yet
    Abstract

    Tabular synthesis is critical for privacy-preserving sharing and augmentation, yet diffusion models rely on implicit mechanisms to capture inter-column relationships. We introduce Geometry-Aware Tabular Diffusion (GATD), which augments tabular diffusion denoisers with pairwise angles and lengths computed from column value differences and used as inputs and auxiliary targets. Our MLP instantiation achieves state-of-the-art benchmark performance while using 3.5x fewer parameters on average (up to 25x for classification tasks): on ten datasets, it wins 8/10 Shape, 7/10 Trend, and 9/10 downstream utility (F1/RMSE), reducing Shape and Trend error by 27% and 20%. Default loss weights transfer to G…

  2. Close
    FinDiff: Diffusion Models for Financial Tabular Data Generation
    Timur Sattarov, Marco Schreyer, Damian Borth · 2023 · Machine Learning · cited 44 times · AI summary available
    Abstract

    The sharing of microdata, such as fund holdings and derivative instruments, by regulatory institutions presents a unique challenge due to strict data confidentiality and privacy regulations. These challenges often hinder the ability of both academics and practitioners to conduct collaborative research effectively. The emergence of generative models, particularly diffusion models, capable of synthesizing data mimicking the underlying distributions of real-world data presents a compelling solution. This work introduces 'FinDiff', a diffusion model designed to generate real-world financial tabular data for a variety of regulatory downstream tasks, for example economic scenario modeling, stress …

  3. Close Uses this paper in depth
    Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Features
    Markus Mueller, Kathrin Gruber, Dennis Fok · 2026 · arXiv.org · preprint, not peer reviewed · cited 5 times · Not summarized yet
    Abstract

    Advances in generative modeling have recently been adapted to tabular data containing discrete and continuous features. However, generating mixed-type features that combine discrete states with an otherwise continuous distribution in a single feature remains challenging. We advance the state-of-the-art in diffusion models for tabular data with a cascaded approach. We first generate a low-resolution version of a tabular data row, that is, the collection of the purely categorical features and a coarse categorical representation of numerical features. Next, this information is leveraged in the high-resolution flow matching model via a novel guided conditional probability path and data-dependent…

  4. Close Uses this paper in depth
    Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion
    Aditya Shankar, Yuan-Dou Wang, Rihan Hai et al. · 2026 · arXiv.org · preprint, not peer reviewed · cited 3 times · Not summarized yet
    Abstract

    Generating tabular data under conditions is critical to applications requiring precise control over the generative process. Existing methods rely on training-time strategies that do not generalise to unseen constraints during inference, and struggle to handle conditional tasks beyond tabular imputation. While manifold theory offers a principled way to guide generation, current formulations are tied to specific inference-time objectives and are limited to continuous domains. We extend manifold theory to tabular data and expand its scope to handle diverse inference-time objectives. On this foundation, we introduce HARPOON, a tabular diffusion method that guides unconstrained samples along the …

  5. Close
    Diffusion GAN-Based Oversampling for Imbalanced Tabular Data
    Shiqi Ren, Jin-Liang Ding, Yiu-Ming Cheung · 2026 · IEEE Transactions on Knowledge and Data Engineering · cited 6 times · Not summarized yet
    Abstract

    Imbalanced class distribution disrupts the training of a classifier, resulting in biases favoring majority classes. Data oversampling is a common strategy to tackle this issue. However, traditional methods may generate incorrect and unnecessary instances when facing complex data challenges, such as class overlap, small disjuncts, and noise samples. Therefore, there is a need for an oversampling method that can accurately characterize the data distribution. This paper introduces a novel deep generative oversampling approach for balancing the imbalanced tabular data by leveraging diffusion models and Generative Adversarial Networks (GANs). The model comprises a generator constructed from diffu…

How are these papers found?

We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.

Updated on 4 November 2026.

The illustrated guide to the papers around a paper