Research map / Federated learning and privacy / Differential privacy
Task-level Differentially Private Meta Learning
Xinyu Zhou, Raef Bassily
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use task-level DP meta learning instead of local training | Ameta (task-level DP meta learning) · synthetic linear regression, single cluster | transfer risk | Improved |
| vary privacy budget epsilon among 1, 3, 10 versus non-private | Ameta · synthetic linear regression, single cluster | transfer risk | No clear effect |
| increase number of meta models q from 1 to 3 (ablation) | Ameta-cluster · synthetic linear regression, 3 clusters | transfer risk | Improved |
| vary privacy epsilon (3 vs 10) at fixed number of clusters (ablation) | Ameta-cluster · synthetic linear regression, 3 clusters | transfer risk | No clear effect |
Closest papers by meaning
- Differentially Private Meta-Learning (ICLR 2020 · similarity 0.92)
- Model-Protected Multi-Task Learning (TPAMI 2020 · similarity 0.89)
- Improving the Variance of Differentially Private Randomized Experiments through Clustering (ICML 2025 · similarity 0.85)
- It's My Data Too: Private ML for Datasets with Multi-User Training Examples (ICML 2025 · similarity 0.85)
- On the Price of Differential Privacy for Hierarchical Clustering (ICLR 2025 · similarity 0.85)
- Noise-Aware Differentially Private Regression via Meta-Learning (NeurIPS 2024 · similarity 0.85)
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.
