# Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

arXiv: https://arxiv.org/abs/2511.13893 · HTML: https://mlsanity.com/paper/2511.13893/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data](https://mlsanity.com/paper/2201.12677/) (2022)
- [Benchmarking Differentially Private Synthetic Data Generation Algorithms](https://mlsanity.com/paper/2112.09238/) (2021)
- [DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation](https://mlsanity.com/paper/2002.11603/) (2020)
- [Graphical-model based estimation and inference for differential privacy](https://mlsanity.com/paper/1901.09136/) (2019)
- [Individual Privacy Accounting via a Renyi Filter](https://mlsanity.com/paper/2008.11193/) (2020)
- [Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods](https://mlsanity.com/paper/2106.07153/) (2021)
- [New Oracle-Efficient Algorithms for Private Synthetic Data Release](https://mlsanity.com/paper/2007.05453/) (2020)
- [Private Synthetic Data for Multitask Learning and Marginal Queries](https://mlsanity.com/paper/2209.07400/) (2022)
- [Privacy Odometers and Filters: Pay-as-you-Go Composition](https://mlsanity.com/paper/1605.08294/) (2016)
- [PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions](https://mlsanity.com/paper/1601.03229/) (2016)
- [Generating Private Synthetic Data with Genetic Algorithms](https://mlsanity.com/paper/2306.03257/) (2023)
- [Differentially Private Tabular Data Synthesis using Large Language Models](https://mlsanity.com/paper/2406.01457/) (2024)
- [Benchmarking Differentially Private Tabular Data Synthesis](https://mlsanity.com/paper/2504.14061/) (2025)
- [DP-TBART: A Transformer-based Autoregressive Model for Differentially Private Tabular Data Generation](https://mlsanity.com/paper/2307.10430/) (2023)
- [PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining](https://mlsanity.com/paper/2311.12850/) (2023)
- [DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis](https://mlsanity.com/paper/2503.14681/) (2025)
- [Privacy-Preserving Synthetic Location Data in the Real World](https://mlsanity.com/paper/2108.02089/) (2021)
- [Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data](https://mlsanity.com/paper/2403.07797/) (2024)
- [From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis](https://mlsanity.com/paper/2504.01395/) (2025)
- [Privately generating tabular data using language models](https://mlsanity.com/paper/2306.04803/) (2023)

## Abstract (arXiv)

In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely correlated datasets, where intricate dependencies can overwhelm statistical models. In such complex scenarios, neural networks are more suitable due to their capacity to fit complex distributions by learning directly from samples. Despite this potential, existing NN-based algorithms still suffer from significant limitations. We therefore propose MargNet, incorporating successful algorithmic designs of statistical models into neural networks. MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals. On sparsely correlated datasets, our approach achieves utility close to the best statistical method while offering an average 7× speedup over it. More importantly, on densely correlated datasets, MargNet establishes a new state-of-the-art, reducing fidelity error by up to 26% compared to the previous best. We release our code on GitHub.footnotehttps://github.com/KaiChen9909/margnet