mlsanityData to 14 Oct 2026

Diffusion Transformers for Tabular Data Time Series Generation

arXiv 2504.07566 ↗First posted 10 Apr 2025cs.LG cs.AIcited by 5

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

Abstract (arXiv)

Tabular data generation has recently attracted a growing interest due to its different application scenarios. However, generating time series of tabular data, where each element of the series depends on the others, remains a largely unexplored domain. This gap is probably due to the difficulty of jointly solving different problems, the main of which are the heterogeneity of tabular data (a problem common to non-time-dependent approaches) and the variable length of a time series. In this paper, we propose a Diffusion Transformers (DiTs) based approach for tabular data series generation. Inspired by the recent success of DiTs in image and video generation, we extend this framework to deal with heterogeneous data and variable-length sequences. Using extensive experiments on six datasets, we show that the proposed approach outperforms previous work by a large margin.

Key facts. Cited by 5 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 32 of its 46 references that are in the map. First posted on arXiv 10 Apr 2025.

Builds on

32 of 46 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space14 Oct
  2. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesis25 Apr
  3. 2022Diffusion models for missing value imputation in tabular data31 Oct
  4. 2022STaSy: Score-based Tabular data Synthesis8 Oct
  5. 2022TabDDPM: Modelling Tabular Data with Diffusion Models30 Sep

Other references · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  9. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  10. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  11. 2019Modeling Tabular data using Conditional GANcited by 699
  12. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
15 more
  1. 2022Language Models are Realistic Tabular Data Generatorscited by 294
  2. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  3. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  4. 2022Can Foundation Models Wrangle Your Data?cited by 175
  5. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  6. 2023REaLTabFormer: Generating Realistic Relational and Tabular Data using Transformerscited by 94
  7. 2024FiT: Flexible Vision Transformer for Diffusion Modelcited by 85
  8. 2020Tabular Transformers for Modeling Multivariate Time Seriescited by 77
  9. 2023Synthcity: facilitating innovative use cases of synthetic data in different data modalitiescited by 76
  10. 2017Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Recordscited by 36
  11. 2023TabMT: Generating tabular data with masked transformerscited by 36
  12. 2022SOS: Score-based Oversampling for Tabular Datacited by 29
  13. 2021Adversarial Attacks on Deep Models for Financial Transaction Recordscited by 24
  14. 2023One Transformer for All Time Series: Representing and Training with Time-Dependent Heterogeneous Tabular Datacited by 13
  15. 2020Using generative adversarial networks to synthesize artificial financial datasetscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025FaultDiffusion: Few-Shot Fault Time Series Generation with Diffusion Modelcited by 1
  2. 2026TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenizationcited by 0
  3. 2026Accelerating Reproducible Research in Synthetic EHR Generationcited by 0
  4. 2026Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Datacited by 0
  5. 2026Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspectivecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters
  2. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generation
  3. 2026Generating Benchmark Health Data Using a Tabular Diffusion Transformer
  4. 2023Continuous Diffusion for Mixed-Type Tabular Data
  5. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generation
  6. 2026Extending Tabular Denoising Diffusion Probabilistic Models for Time-Series Data Generation
  7. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
  8. 2025T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models