Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis]
Summary: Benchmark and unified evaluation framework for DP tabular data synthesis that standardizes preprocessing, feature selection, and synthesis for fair, comprehensive comparisons. Module-level experiments reveal a utility–efficiency trade-off (statistical methods favor utility; deep models favor efficiency) and provide theoretical insights; code open-sourced. (summarized by gpt-5-mini on Feb 11 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Kai Chen (University of Virginia)
- 2. Xiaochen Li (University of North Carolina at Greensboro)
- 3. Chen Gong (University of Virginia)
- 4. Ryan McKenna (Google)
- 5. Tianhao Wang (University of Virginia)
BibTeX Citation
@inproceedings{chen_sigmod26,
title = {{Benchmarking Differentially Private Tabular Data Synthesis: [Experiments \& Analysis]}},
author = {Chen, Kai and Li, Xiaochen and Gong, Chen and McKenna, Ryan and Wang, Tianhao},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3769764},
url = {https://dl.acm.org/doi/10.1145/3769764},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,254 | HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings | 2026 | SIGMOD | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 5 of 5 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,308 | PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions | 2016 | SIGMOD | 0.00011216361 |
| 2,167 | Optimizing error of high-dimensional statistical queries under differential privacy | 2018 | VLDB | 9.047803e-05 |
| 2,476 | Data Synthesis via Differentially Private Markov Random Fields | 2021 | VLDB | 8.5258582e-05 |
| 2,841 | AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data | 2022 | VLDB | 8.0637668e-05 |
| 3,016 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB | 7.8484858e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 3,939 | DPSynthesizer: Differentially Private Data Synthesizer for Privacy Preserving Data Sharing | 2014 | VLDB |
| 2 | 11,130 | Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections | 2024 | PODS |
| 3 | 10,967 | Privacy-Enhanced Database Synthesis for Benchmark Publishing | 2025 | VLDB |
| 4 | 7,909 | Differentially Private Data Generation with Missing Data | 2024 | VLDB |
| 5 | 11,459 | Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy | 2023 | VLDB |
| 6 | 2,476 | Data Synthesis via Differentially Private Markov Random Fields | 2021 | VLDB |
| 7 | 2,129 | Data Synthesis based on Generative Adversarial Networks | 2018 | VLDB |
| 8 | 3,016 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB |
| 9 | 10,254 | HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings | 2026 | SIGMOD |
| 10 | 8,514 | Synthetic Tabular Data: Methods, Attacks and Defenses | 2025 | VLDB |