mlsanityData to 7 Oct 2026

STaSy: Score-based Tabular data Synthesis

arXiv 2210.04018 ↗First posted 8 Oct 2022cs.LG cs.AI cs.DBcited by 85

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

Abstract (arXiv)

Tabular data synthesis is a long-standing research topic in machine learning. Many different methods have been proposed over the past decades, ranging from statistical methods to deep generative methods. However, it has not always been successful due to the complicated nature of real-world tabular data. In this paper, we present a new model named Score-based Tabular data Synthesis (STaSy) and its training strategy based on the paradigm of score-based generative modeling. Despite the fact that score-based generative models have resolved many issues in generative models, there still exists room for improvement in tabular data synthesis. Our proposed training strategy includes a self-paced learning technique and a fine-tuning strategy, which further increases the sampling quality and diversity by stabilizing the denoising score matching training. Furthermore, we also conduct rigorous experimental studies in terms of the generative task trilemma: sampling quality, diversity, and time. In our experiments with 15 benchmark tabular datasets and 7 baselines, our method outperforms existing methods in terms of task-dependant evaluations and diversity. Code is available at https://github.com/JayoungKim408/STaSy.

Key facts. Cited by 85 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 16 of its 62 references that are in the map. First posted on arXiv 8 Oct 2022.

Builds on

16 of 62 references.

References · 16

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2019Modeling Tabular data using Conditional GANcited by 695
  4. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  5. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  6. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  7. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  8. 2020How to train your neural ODE: the world of Jacobian and kinetic regularizationcited by 228
  9. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  10. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  11. 2017Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Recordscited by 36
  12. 2022SOS: Score-based Oversampling for Tabular Datacited by 29
4 more
  1. 2021OCT-GAN: Neural ODE-based Conditional Tabular GANscited by 27
  2. 2022Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesiscited by 24
  3. 2018Generating Synthetic but Plausible Healthcare Record Datasetscited by 12
  4. 2018Correlated discrete data generation using adversarial trainingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 27; 2025: 22; 2026: 22.

85 papers.

Sort:

By area:

  1. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 183
  2. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  3. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
  4. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 60
  5. 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 60
  6. 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
  7. 2023MissDiff: Training Diffusion Models on Tabular Data with Missing Valuescited by 38
  8. 2023TabMT: Generating tabular data with masked transformerscited by 36
  9. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  10. 2024ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Modelscited by 28
  11. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  12. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizingcited by 24
38 more
  1. 2024A Survey on Statistical Theory of Deep Learning: Approximation, Training Dynamics, and Generative Modelscited by 20
  2. 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spacescited by 19
  3. 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintscited by 18
  4. 2024Systematic Assessment of Tabular Data Synthesiscited by 17
  5. 2023Continuous Diffusion for Mixed-Type Tabular Datacited by 16
  6. 2024Self-Supervision Improves Diffusion Models for Tabular Data Imputationcited by 16
  7. 2024Diffusion Models for Tabular Data Imputation and Synthetic Data Generationcited by 15
  8. 2024Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AIcited by 15
  9. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 15
  10. 2025TabularARGN: A Flexible and Efficient Auto-Regressive Framework for Generating High-Fidelity Synthetic Datacited by 13
  11. 2025A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyondcited by 13
  12. 2023On the Usefulness of Synthetic Tabular Data Generationcited by 12
  13. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 12
  14. 2024Balanced Mixed-Type Tabular Data Synthesis with Diffusion Modelscited by 12
  15. 2024Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Modelscited by 12
  16. 2024SiloFuse: Cross-silo Synthetic Data Generation with Latent Tabular Diffusion Modelscited by 10
  17. 2025TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationcited by 10
  18. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  19. 2025Diffusion and Flow Matching Models for Tabular Data: A Surveycited by 8
  20. 2025LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusioncited by 8
  21. 2023A Comprehensive Survey on Generative Diffusion Models for Structured Datacited by 7
  22. 2023Boosting Data Analytics With Synthetic Volume Expansioncited by 7
  23. 2024Structured Evaluation of Synthetic Tabular Datacited by 7
  24. 2024Causality for Tabular Data Synthesis: A High-Order Structure Causal Benchmark Frameworkcited by 7
  25. 2024Understanding and Mitigating Memorization in Diffusion Models for Tabular Datacited by 7
  26. 2024Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspectivecited by 5
  27. 2024Guided Discrete Diffusion for Electronic Health Record Generationcited by 5
  28. 2024Scaling Up Diffusion and Flow-based XGBoost Modelscited by 5
  29. 2025TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representationcited by 5
  30. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 5
  31. 2023PriSampler: Mitigating Property Inference of Diffusion Modelscited by 4
  32. 2024TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Datacited by 4
  33. 2024Unmasking Trees for Tabular Datacited by 4
  34. 2024Targeted synthetic data generation for tabular data via hardness characterizationcited by 4
  35. 2024Diffusion-nested Auto-Regressive Synthesis of Heterogeneous Tabular Datacited by 4
  36. 2025Diffusion Transformers for Tabular Data Time Series Generationcited by 4
  37. 2026Cascaded Flow Matching for Heterogeneous Tabular Data with Mixed-Type Featurescited by 4
  38. 2025CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generationcited by 3

50 most cited of 85 All 85 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026XGenBoost: Synthesizing Small and Large Tabular Datasets with XGBoost
  2. 2024CTSyn: A Foundation Model for Cross Tabular Data Generation
  3. 2024LaTable: Towards Large Tabular Models
  4. 2020Tabular GANs for uneven distribution
  5. 2025RecTable: Fast Modeling Tabular Data with Rectified Flow
  6. 2024A Good Score Does not Lead to A Good Generative Model
  7. 2023TabuLa: Harnessing Language Models for Tabular Data Synthesis
  8. 2026Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training