HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings
Summary: HeteroFedSyn is the first DP tabular-data synthesis framework for heterogeneous horizontal federated learning, extending PrivSyn’s 2-way marginals. It combines noise-efficient projected dependency estimation, multiplicative-noise correction, and adaptive marginal selection to approach centralized utility. (summarized by gpt-5.6-luna on Jul 26 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Xiaochen Li (University of North Carolina at Greensboro)
- 2. Fengyu Gao (University of Virginia)
- 3. Xizixiang Wei (University of Virginia)
- 4. Tianhao Wang (University of Virginia)
- 5. Cong Shen (University of Virginia)
- 6. Jing Yang (University of Virginia)
BibTeX Citation
@inproceedings{li_sigmod26,
title = {{HeteroFedSyn: Differentially Private Tabular Data Synthesis for Heterogeneous Federated Settings}},
author = {Li, Xiaochen and Gao, Fengyu and Wei, Xizixiang and Wang, Tianhao and Shen, Cong and Yang, Jing},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3802072},
url = {https://dl.acm.org/doi/10.1145/3802072},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,155 | PrivBayes: Private Data Release via Bayesian Networks | 2014 | SIGMOD | 0.00011777587 |
| 1,528 | A Data- and Workload-Aware Algorithm for Range Queries Under Differential Privacy | 2014 | VLDB | 0.00010349919 |
| 2,533 | Data Synthesis via Differentially Private Markov Random Fields | 2021 | VLDB | 8.3345608e-05 |
| 2,902 | AIM: An Adaptive and Iterative Mechanism for Differentially Private Synthetic Data | 2022 | VLDB | 7.8828375e-05 |
| 3,078 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB | 7.6723869e-05 |
| 3,329 | Answering Range Queries Under Local Differential Privacy | 2019 | SIGMOD | 7.4187944e-05 |
| 9,477 | SPAS: Continuous Release of Data Streams under w-Event Differential Privacy | 2025 | SIGMOD | 5.1708619e-05 |
| 10,546 | Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis] | 2026 | SIGMOD | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 8,683 | Synthetic Tabular Data: Methods, Attacks and Defenses | 2025 | VLDB |
| 2 | 3,292 | Kamino: Constraint-Aware Differentially Private Data Synthesis | 2021 | VLDB |
| 3 | 11,090 | Private Synthetic Data Generation in Bounded Memory | 2025 | PODS |
| 4 | 8,092 | PSynDB: Accurate and Accessible Private Data Generation | 2019 | VLDB |
| 5 | 3,078 | Plausible Deniability for Privacy-Preserving Data Synthesis | 2017 | VLDB |
| 6 | 4,541 | Projected Federated Averaging with Heterogeneous Differential Privacy | 2022 | VLDB |
| 7 | 3,983 | DPSynthesizer: Differentially Private Data Synthesizer for Privacy Preserving Data Sharing | 2014 | VLDB |
| 8 | 5,868 | Federated Heavy Hitter Analytics with Local Differential Privacy | 2025 | SIGMOD |
| 9 | 2,533 | Data Synthesis via Differentially Private Markov Random Fields | 2021 | VLDB |
| 10 | 10,546 | Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis] | 2026 | SIGMOD |