English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Generative models trained with Differential Privacy (DP) are increasinglyused to produce synthetic data while reducing privacy risks. Navigating theirspecific privacy-utility tradeoffs makes it challenging to determine whichmodels would work best for specific settings/tasks. In this paper, we fill thisgap in the context of tabular data by analyzing how DP generative modelsdistribute privacy budgets across rows and columns, arguably the main source ofutility degradation. We examine the main factors contributing to how privacybudgets are spent, including underlying modeling techniques, DP mechanisms, anddata dimensionality.  Our extensive evaluation of both graphical and deep generative models shedslight on the distinctive features that render them suitable for differentsettings and tasks. We show that graphical models distribute the privacy budgethorizontally and thus cannot handle relatively wide datasets while theperformance on the task they were optimized for monotonically increases withmore data. Deep generative models spend their budget per iteration, so theirbehavior is less predictable with varying dataset dimensions but could performbetter if trained on more features. Also, low levels of privacy($\epsilon\geq100$) could help some models generalize, achieving better resultsthan without applying DP.

Understanding how Differentially Private Generative Models Spend their Privacy Budget