The Library
Mitigating statistical bias within differentially private synthetic data
Tools
Ghalebikesabi, Sahra, Wilde, Harrison, Jewson, Jack, Doucet, Arnaud, Vollmer, Sebastian and Holmes, Chris (2022) Mitigating statistical bias within differentially private synthetic data. In: Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, Eindhoven, The Netherlands, 01-05 Aug 2022. Published in: Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, 180 pp. 696-705.
|
PDF
WRAP-Mitigating-statistical-bias-within-differentially-private-synthetic-data-Harrison-2022.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (980Kb) | Preview |
Official URL: https://proceedings.mlr.press/v180/ghalebikesabi22...
Abstract
Increasing interest in privacy-preserving machine learning has led to new and evolved approaches for generating private synthetic data from undisclosed real data. However, mechanisms of privacy preservation can significantly reduce the utility of synthetic data, which in turn impacts downstream tasks such as learning predictive models or inference. We propose several re-weighting strategies using privatised likelihood ratios that not only mitigate statistical bias of downstream estimators but also have general applicability to differentially private generative models. Through large-scale empirical evaluation, we show that private importance weighting provides simple and effective privacy-compliant augmentation for general applications of synthetic data.
Item Type: | Conference Item (Paper) | ||||||||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software |
||||||||||||||||||||||||||||||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | ||||||||||||||||||||||||||||||||||||
Library of Congress Subject Headings (LCSH): | Machine learning -- Security measures, Computer security, Computer networks -- Security measures, Mathematical statistics, Databases -- Statistics, Data protection, Data encryption (Computer science), Computers and civilization | ||||||||||||||||||||||||||||||||||||
Journal or Publication Title: | Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence | ||||||||||||||||||||||||||||||||||||
Publisher: | PMLR | ||||||||||||||||||||||||||||||||||||
Official Date: | 2022 | ||||||||||||||||||||||||||||||||||||
Dates: |
|
||||||||||||||||||||||||||||||||||||
Volume: | 180 | ||||||||||||||||||||||||||||||||||||
Page Range: | pp. 696-705 | ||||||||||||||||||||||||||||||||||||
Status: | Peer Reviewed | ||||||||||||||||||||||||||||||||||||
Publication Status: | Published | ||||||||||||||||||||||||||||||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||||||||||||||||||||||||||||||
Date of first compliant deposit: | 29 March 2023 | ||||||||||||||||||||||||||||||||||||
Date of first compliant Open Access: | 29 March 2023 | ||||||||||||||||||||||||||||||||||||
RIOXX Funder/Project Grant: |
|
||||||||||||||||||||||||||||||||||||
Conference Paper Type: | Paper | ||||||||||||||||||||||||||||||||||||
Title of Event: | Thirty-Eighth Conference on Uncertainty in Artificial Intelligence | ||||||||||||||||||||||||||||||||||||
Type of Event: | Conference | ||||||||||||||||||||||||||||||||||||
Location of Event: | Eindhoven, The Netherlands | ||||||||||||||||||||||||||||||||||||
Date(s) of Event: | 01-05 Aug 2022 | ||||||||||||||||||||||||||||||||||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year