Supporting Database Constraints in Synthetic Data Generation based on Generative Adversarial Networks

Summary: Extends Tabular GAN (TGAN) to enforce relational DB constraints during synthetic data generation, enabling constraint-preserving data for privacy benchmarking. Prototype evaluates extensions on real schemas, showing fidelity-constraint tradeoffs. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 5908
Venue: SIGMOD
Year: 2020
Pagerank: 5.3639369e-05
Overall Rank: 8,815 | 39.53%
DOI: 10.1145/3318464.3384414

Incoming Non-self Citations Over Time

Authors

1. Wanxin Li (University of Waterloo)

BibTeX Citation

@inproceedings{li_sigmod20,
        title = {{Supporting Database Constraints in Synthetic Data Generation based on Generative Adversarial Networks}},
        author = {Li, Wanxin},
        series = {{SIGMOD} '20},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3318464.3384414},
        url = {https://dl.acm.org/doi/10.1145/3318464.3384414},
        year = {2020}
}

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
3,907	Accelerating Approximate Aggregation Queries with Expensive Predicates	2021	VLDB	7.0278233e-05

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
494	Dependencies Revisited for Improving Data Quality	2008	PODS	0.00017526549
2,129	Data Synthesis based on Generative Adversarial Networks	2018	VLDB	9.1266572e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	10,317	Guardrail: Automated Integrity Constraint Synthesis From Noisy Data	2026	SIGMOD
2	10,345	Benchmarking Differentially Private Tabular Data Synthesis: [Experiments & Analysis]	2026	SIGMOD
3	3,016	Plausible Deniability for Privacy-Preserving Data Synthesis	2017	VLDB
4	13,351	Turning Databases Into Generative AI Machines	2024	CIDR
5	3,412	Kamino: Constraint-Aware Differentially Private Data Synthesis	2021	VLDB
6	5,169	LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning	2022	SIGMOD
7	8,514	Synthetic Tabular Data: Methods, Attacks and Defenses	2025	VLDB
8	2,369	Data Generation using Declarative Constraints	2011	SIGMOD
9	2,129	Data Synthesis based on Generative Adversarial Networks	2018	VLDB
10	4,261	Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration	2020	VLDB