Research map / Federated learning and privacy / Differential privacy
Differentially Private Meta-Learning
Jeffrey Li, Mikhail Khodak, Sebastian Caldas, Ameet Talwalkar
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-global DP instead of local DP | Reptile · Shakespeare-800 and Wiki-1600 | accuracy relative to non-private accuracy: 78%,88%, and 92% vs. about 55%; 72%, 82%, and 83% vs. about 50% | Improved |
| Use task-global DP instead of non-private training | Reptile · Shakespeare-800 and Wiki-1600 | accuracy relative to non-private accuracy: 78%,88%, and 92%; 72%, 82%, and 83% | Hurt |
| Apply task-global DP during meta-training | Reptile · Omniglot and Mini-ImageNet 5-shot-5-way | meta-test accuracy | Improved |
| Apply local DP during meta-training | Reptile · Omniglot and Mini-ImageNet 5-shot-5-way | meta-test accuracy | Hurt |
| Increase the number of training shots | Task-global DP Reptile · Omniglot and Mini-ImageNet 5-shot-5-way | meta-test accuracy | Improved |
Closest papers by meaning
- Task-level Differentially Private Meta Learning (NeurIPS 2022 · similarity 0.92)
- Certification for Differentially Private Prediction in Gradient-Based Training (ICML 2025 · similarity 0.87)
- Differentially Private Prototypes for Imbalanced Transfer Learning (AAAI 2025 · similarity 0.87)
- Online Sensitivity Optimization in Differentially Private Learning (AAAI 2024 · similarity 0.87)
- Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining (ICML 2024 · similarity 0.87)
- Privacy-Preserving Personalized Federated Prompt Learning for Multimodal Large Language Models (ICLR 2025 · similarity 0.87)
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.
