mlsanityData to 7 Oct 2026

PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure

arXiv 2511.07997 ↗First posted 11 Nov 2025stat.ML cs.CR cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We revisit the problem of generating synthetic data under differential privacy. To address the core limitations of marginal-based methods, we propose the Private Adaptive Generative Adversarial Network with Bayes Network Structure (PrAda-GAN), which integrates the strengths of both GAN-based and marginal-based approaches. Our method adopts a sequential generator architecture to capture complex dependencies among variables, while adaptively regularizing the learned structure to promote sparsity in the underlying Bayes network. Theoretically, we establish diminishing bounds on the parameter distance, variable selection error, and Wasserstein distance. Our analysis shows that leveraging dependency sparsity leads to significant improvements in convergence rates. Empirically, experiments on both synthetic and real-world datasets demonstrate that PrAda-GAN outperforms existing tabular data synthesis methods in terms of the privacy-utility trade-off.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 37 of its 71 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

37 of 71 references.

References · 37

  1. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  3. 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 745
  4. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  5. 2014OpenML: networked science in machine learningcited by 523
  6. 2021Differentially Private Fine-tuning of Language Modelscited by 392
  7. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  8. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 237
  9. 2018Differentially Private Generative Adversarial Networkcited by 235
  10. 2018Subsampled R'enyi Differential Privacy and Analytical Moments Accountantcited by 234
  11. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  12. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
25 more
  1. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  2. 2022AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Datacited by 88
  3. 2021Large Scale Private Learning via Low-rank Reparametrizationcited by 87
  4. 2022Automatic Clipping: Differentially Private Deep Learning Made Easier and Strongercited by 87
  5. 2021Benchmarking Differentially Private Synthetic Data Generation Algorithmscited by 80
  6. 2020DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generationcited by 78
  7. 2019Graphical-model based estimation and inference for differential privacycited by 73
  8. 2022CTAB-GAN+: Enhancing Tabular Data Synthesiscited by 70
  9. 2021Iterative Methods for Private Synthetic Data: Unifying Framework and New Methodscited by 58
  10. 2019G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminatorscited by 53
  11. 2021Differentially Private Stochastic Optimization: New Results in Convex and Non-Convex Settingscited by 45
  12. 2017Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classificationcited by 39
  13. 2023Why Is Public Pretraining Necessary for Private Model Training?cited by 36
  14. 2021An error analysis of generative adversarial networks for learning distributionscited by 35
  15. 2019PPGAN: Privacy-preserving Generative Adversarial Networkcited by 34
  16. 2018Some Theoretical Properties of GANscited by 27
  17. 2020Consistent Feature Selection for Analytic Deep Neural Networkscited by 27
  18. 2021Adversarial Attacks Against Deep Generative Models on Data: A Surveycited by 23
  19. 2023Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithmscited by 7
  20. 2023Optimal Locally Private Nonparametric Classification with Public Datacited by 7
  21. 2025Towards hyperparameter-free optimization with differential privacycited by 7
  22. 2024Tabular Data Synthesis with Differential Privacy: A Surveycited by 6
  23. 2025Dynamic Causal Structure Discovery and Causal Effect Estimationcited by 3
  24. 2025Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Datacited by 3
  25. 2024Better Locally Private Sparse Estimation Given Multiple Samples Per Usercited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Portable Causal Fairness Across Synthetic Data Generator Familiescited by 0