mlsanityData to 7 Oct 2026

Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis

arXiv 2307.15424 ↗First posted 28 Jul 2023cs.LG stat.AP stat.COcited by 7

Not on the map. Why?

Abstract (arXiv)

This article provides a comprehensive synthesis of the recent developments in synthetic data generation via deep generative models, focusing on tabular datasets. We specifically outline the importance of synthetic data generation in the context of privacy-sensitive data. Additionally, we highlight the advantages of using deep generative models over other methods and provide a detailed explanation of the underlying concepts, including unsupervised learning, neural networks, and generative models. The paper covers the challenges and considerations involved in using deep generative models for tabular datasets, such as data normalization, privacy concerns, and model evaluation. This review provides a valuable resource for researchers and practitioners interested in synthetic data generation and its applications.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 66 of its 138 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

66 of 138 references.

References · 66

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2016Deep Learning with Differential Privacycited by 2,682
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2016Density estimation using Real NVPcited by 2,029
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  11. 2016Variational Inference: A Review for Statisticianscited by 1,466
  12. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
38 more
  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2016An overview of gradient descent optimization algorithmscited by 1,021
  3. 2022Diffusion Models in Vision: A Surveycited by 1,008
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  5. 2015Automatic differentiation in machine learning: a surveycited by 846
  6. 2019Modeling Tabular data using Conditional GANcited by 695
  7. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  8. 2017Renyi Differential Privacycited by 643
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  10. 2019Neural Spline Flowscited by 590
  11. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  12. 2015Importance Weighted Autoencoderscited by 454
  13. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  14. 2018Assessing Generative Models via Precision and Recallcited by 401
  15. 2020Understanding the Behaviour of Contrastive Losscited by 397
  16. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  17. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  18. 2013Black Box Variational Inferencecited by 317
  19. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  20. 2015A note on the evaluation of generative modelscited by 291
  21. 2013The Composition Theorem for Differential Privacycited by 290
  22. 2019Monte Carlo Gradient Estimation in Machine Learningcited by 281
  23. 2018Scalable Private Learning with PATEcited by 266
  24. 2019Residual Flows for Invertible Generative Modelingcited by 256
  25. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  26. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  27. 2017Advances in Variational Inferencecited by 236
  28. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  29. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  30. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  31. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  32. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 193
  33. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  34. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 170
  35. 2018Neural Importance Samplingcited by 154
  36. 2018Activation Functions: Comparison of trends in Practice and Research for Deep Learningcited by 130
  37. 2017Improving Generalization Performance by Switching from Adam to SGDcited by 121
  38. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 2.

7 papers.

  1. 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 27
  2. 2024Tabular Data Synthesis with Differential Privacy: A Surveycited by 6
  3. 2024High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASRcited by 2
  4. 2025Probabilistic causal graphs as categorical data synthesizers: Do they do better than Gaussian Copulas and Conditional Tabular GANs?cited by 0
  5. 2025Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generationcited by 0
  6. 2026Generating High-quality Privacy-preserving Synthetic Datacited by 0
  7. 2026Measuring Privacy Risks and Tradeoffs in Financial Synthetic Data Generationcited by 0