mlsanityData to 14 Oct 2026

A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyond

arXiv 2503.05954 ↗First posted 7 Mar 2025cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Generative modelling has become the standard approach for synthesising tabular data. However, different use cases demand synthetic data to comply with different requirements to be useful in practice. In this survey, we review deep generative modelling approaches for tabular data from the perspective of five types of requirements: utility of the synthetic data, alignment of the synthetic data with domain-specific knowledge, statistical fidelity of the synthetic data distribution compared to the real data distribution, privacy-preserving capabilities, and sampling diversity. We group the approaches along two levels of granularity: (i) based on the requirements they address and (ii) according to the underlying model they utilise. Additionally, we summarise the appropriate evaluation methods for each requirement, the relationships among the requirements, and the specific characteristics of each model type. Finally, we discuss future directions for the field, along with opportunities to improve the current evaluation methods. Overall, this survey can be seen as a user guide to tabular data generation: helping readers navigate available models and evaluation methods to find those best suited to their needs.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 53 of its 79 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

53 of 79 references.

References · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2016Deep Learning with Differential Privacycited by 2,728
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  8. 2021Membership Inference Attacks From First Principlescited by 878
  9. 2019Modeling Tabular data using Conditional GANcited by 699
  10. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 674
  11. 2017Wasserstein GANcited by 639
  12. 2019Neural Spline Flowscited by 596
38 more
  1. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 574
  2. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  3. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 434
  4. 2018Assessing Generative Models via Precision and Recallcited by 406
  5. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
  6. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 348
  7. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
  8. 2022Language Models are Realistic Tabular Data Generatorscited by 294
  9. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 200
  10. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  11. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 196
  12. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  13. 2018Data Synthesis based on Generative Adversarial Networkscited by 185
  14. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  15. 2019Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoningcited by 151
  16. 2018Synthesizing Tabular Data using Generative Adversarial Networkscited by 92
  17. 2022AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Datacited by 90
  18. 2022STaSy: Score-based Tabular data Synthesiscited by 86
  19. 2020DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generationcited by 78
  20. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
  21. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  22. 2020Conditional Wasserstein GAN-based Oversampling of Tabular Data for Imbalanced Learningcited by 67
  23. 2023Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Treescited by 62
  24. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 59
  25. 2022Deep Learning with Logical Constraintscited by 44
  26. 2022Adversarial random forests for density estimation and generative modelingcited by 44
  27. 2023FinDiff: Diffusion Models for Financial Tabular Data Generationcited by 41
  28. 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Datacited by 29
  29. 2024TabPFGen -- Tabular Data Generation with TabPFNcited by 28
  30. 2021OCT-GAN: Neural ODE-based Conditional Tabular GANscited by 27
  31. 2022Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesiscited by 24
  32. 2023AutoDiff: combining Auto-encoder and Diffusion model for tabular data synthesizingcited by 24
  33. 2019FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environmentscited by 23
  34. 2023Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmarkcited by 23
  35. 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraintscited by 18
  36. 2023CuTS: Customizable Tabular Synthetic Data Generationcited by 13
  37. 2024Navigating Tabular Data Synthesis Research: Understanding User Needs and Tool Capabilitiescited by 8
  38. 2023Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraintscited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 11.

15 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
  2. 2025Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphscited by 9
  3. 2026TabFORGE: A Tabular Foundation Model for Generative Modellingcited by 3
  4. 2025Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoderscited by 1
  5. 2026AI-Native Closed-Loop Security for 6G-Enabled Cyber-Physical Systems: From Edge Detection to Network-Wide Mitigationcited by 1
  6. 2026Diff-DDoS: Realistic Cyber-Physical Attack Synthesis and Robust Detection for 5G-Enabled CPS Using Tabular Diffusion Modelscited by 1
  7. 2026Rethinking Data Augmentation under Covariate Shift: Invariant-Guided Diffusion and Prototype Reweightingcited by 1
  8. 2025A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCitycited by 0
  9. 2026Generating High-quality Privacy-preserving Synthetic Datacited by 0
  10. 2026On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metricscited by 0
  11. 2026Constraint-Aware Synthetic Tabular Data Generation via Inter-Column Constraint Discovery with LLM Agentscited by 0
  12. 2026CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular Datacited by 0
3 more
  1. 2026MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular Generationcited by 0
  2. 2026Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interactioncited by 0
  3. 2026Beyond Distributional Fidelity: Causal-Penalized Diffusion for Synthetic Tabular Datacited by 0