AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

PetaGAIL++: Utility Optimized Private Trajectory Generation with Imitation Learning

Yingjie Ma, Bijal Bharadva, Xin Zhang, Joann Qiongna Chen

ICLR 2026 · Federated learning and privacy › Differential privacy · approach: Differentially private synthetic data

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
Add sensitivity-aware noise allocation and WGAN-GP to PATEGAILPATEGAIL · Geolife noise 0.10DailyLoc JSD: 0.6915 -> 0.4914Improved
Add sensitivity-aware noise allocation and WGAN-GP to PATEGAILPATEGAIL · Geolife noise 0.10I-Rank JSD: 0.2698 -> 0.0607Improved
Add sensitivity-aware noise allocation and WGAN-GP to PATEGAILPATEGAIL · Geolife noise 0.10G-Rank JSD: 0.0512 -> 0.0278Improved
Add sensitivity-aware noise allocation and WGAN-GP to PATEGAILPATEGAIL · Geolife noise 0.01Radius JSD: 0.0260 -> 0.0409No clear effect
Add PATEGAIL++ to PATEGAIL under white-box membership inferencePATEGAIL · Geolife noise 0.01MIA AUC: 0.7208 -> 0.4962Improved
Add PATEGAIL++ to PATEGAIL under LiRAPATEGAIL · GeolifeLiRA attack accuracy: 0.7000 -> 0.6088Improved
Add PATEGAIL++ to PATEGAIL on Telecom ShanghaiPATEGAIL · Telecom Shanghai noise 0.01Distance JSD: 0.1251 -> 0.0052Improved
Add PATEGAIL++ to PATEGAIL on Telecom Shanghai at large noisePATEGAIL · Telecom Shanghai noise 1.00DailyLoc JSD: 0.5554 -> 0.6252Hurt
Add sensitivity-aware aggregation at user level in the LDP setting (ablation)PATEGAIL++ (LDP) · Geolife noise 1.00DailyLoc JSD: 0.6084 -> 0.3758Improved
Add sensitivity-aware aggregation at user level in the LDP setting (ablation)PATEGAIL++ (LDP) · Geolife noise 0.10DailyLoc JSD: 0.6003 -> 0.6916Hurt
Vary gradient penalty coefficient lambda_GP over 1, 5, 10, 15, 20 (ablation)PATEGAIL++ · Geolifeutility metrics: 0.0216 -> 0.0512Mixed
Use only 40% of users instead of all users (ablation)PATEGAIL++ · Geolife noise 0.01DailyLoc JSD: 0.6917 -> 0.6084No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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