Differentially Private Normalizing Flows for Synthetic Tabular Data Generation

Jaewoo Lee, Minjung Kim, Yonghyun Jeong, Youngmin Ro

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations


Normalizing flows have shown to be a promising approach to deep generative modeling due to their ability to exactly evaluate density - other alternatives either implicitly model the density or use approximate surrogate density. In this work, we present a differentially private normalizing flow model for heterogeneous tabular data. Normalizing flows are in general not amenable to differentially private training because they require complex neural networks with larger depth (compared to other generative models) and use specialized architectures for which per-example gradient computation is difficult (or unknown). To reduce the parameter complexity, the proposed model introduces a conditional spline flow which simulates transformations at different stages depending on additional input and is shared among sub-flows. For privacy, we introduce two fine-grained gradient clipping strategies that provide a better signal-to-noise ratio and derive fast gradient clipping methods for layers with custom parameterization. Our empirical evaluations show that the proposed model preserves statistical properties of original dataset better than other baselines.

Original languageEnglish
Title of host publicationAAAI-22 Technical Tracks 7
PublisherAssociation for the Advancement of Artificial Intelligence
Number of pages9
ISBN (Electronic)1577358767, 9781577358763
StatePublished - 30 Jun 2022
Event36th AAAI Conference on Artificial Intelligence, AAAI 2022 - Virtual, Online
Duration: 22 Feb 20221 Mar 2022

Publication series

NameProceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022


Conference36th AAAI Conference on Artificial Intelligence, AAAI 2022
CityVirtual, Online


Dive into the research topics of 'Differentially Private Normalizing Flows for Synthetic Tabular Data Generation'. Together they form a unique fingerprint.

Cite this