AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Differentially Private Synthetic Data Generation for Relational Databases

Kaveh Alim, Hao Wang, Ojas Gulati, Akash Srivastava, Navid Azizan

JMLR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase privacy budget eps_rel for establishing relationships (ablation)Relational DP synthetic data algorithm (AIM, MST) · MovieLens and IPUMSaverage 3-way cross-table marginal errorImproved
increase number of iterations T (ablation)Relational DP synthetic data algorithm · MovieLens and IPUMSaverage 3-way marginal error: optimal range T = 10 to T = 15Mixed
vary budget split alpha between exponential and Gaussian mechanisms (ablation)Relational DP synthetic data algorithm · MovieLens and IPUMSaverage 3-way marginal error: alpha = 0.2 selectedMixed
vary number of workloads K selected by the exponential mechanism (ablation)Relational DP synthetic data algorithm · MovieLens and IPUMSaverage 3-way marginal errorMixed
optimize more highest-error workloads per relaxed optimization step (ablation)Relaxed optimization via projected gradient descent · MovieLens and IPUMSaverage 3-way marginal errorImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy