Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent

Konstantin Donhauser, Javier Abad, Neha Hulkund, Fanny Yang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:11453-11473, 2024.

Abstract

We present a novel approach for differentially private data synthesis of protected tabular datasets, a relevant task in highly sensitive domains such as healthcare and government. Current state-of-the-art methods predominantly use marginal-based approaches, where a dataset is generated from private estimates of the marginals. In this paper, we introduce PrivPGD, a new generation method for marginal-based private data synthesis, leveraging tools from optimal transport and particle gradient descent. Our algorithm outperforms existing methods on a large range of datasets while being highly scalable and offering the flexibility to incorporate additional domain-specific constraints.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-donhauser24a, title = {Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent}, author = {Donhauser, Konstantin and Abad, Javier and Hulkund, Neha and Yang, Fanny}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {11453--11473}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/donhauser24a/donhauser24a.pdf}, url = {https://proceedings.mlr.press/v235/donhauser24a.html}, abstract = {We present a novel approach for differentially private data synthesis of protected tabular datasets, a relevant task in highly sensitive domains such as healthcare and government. Current state-of-the-art methods predominantly use marginal-based approaches, where a dataset is generated from private estimates of the marginals. In this paper, we introduce PrivPGD, a new generation method for marginal-based private data synthesis, leveraging tools from optimal transport and particle gradient descent. Our algorithm outperforms existing methods on a large range of datasets while being highly scalable and offering the flexibility to incorporate additional domain-specific constraints.} }
Endnote
%0 Conference Paper %T Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent %A Konstantin Donhauser %A Javier Abad %A Neha Hulkund %A Fanny Yang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-donhauser24a %I PMLR %P 11453--11473 %U https://proceedings.mlr.press/v235/donhauser24a.html %V 235 %X We present a novel approach for differentially private data synthesis of protected tabular datasets, a relevant task in highly sensitive domains such as healthcare and government. Current state-of-the-art methods predominantly use marginal-based approaches, where a dataset is generated from private estimates of the marginals. In this paper, we introduce PrivPGD, a new generation method for marginal-based private data synthesis, leveraging tools from optimal transport and particle gradient descent. Our algorithm outperforms existing methods on a large range of datasets while being highly scalable and offering the flexibility to incorporate additional domain-specific constraints.
APA
Donhauser, K., Abad, J., Hulkund, N. & Yang, F.. (2024). Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:11453-11473 Available from https://proceedings.mlr.press/v235/donhauser24a.html.

Related Material