Research map / Federated learning and privacy / Differential privacy
Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 APES instead of UniS | FedProx on QMNIST · QMNIST, Uniform2 | accuracy: 77.54% -> 79.67% | Helped |
| Use APES instead of PLDP | FedProx on QMNIST · QMNIST, Uniform2 | accuracy: 77.54% -> 79.67% | Helped |
| Use APES instead of UniS | FedProx on QMNIST · QMNIST, Uniform2 | central user-level privacy εᵘᶜ: 76.9 -> 57.6 | Helped |
| Use APES instead of PLDP | FedProx on QMNIST · QMNIST, Uniform2 | central user-level privacy εᵘᶜ: 7850 -> 57.6 | Helped |
| Add post-sparsification to APES (ablation) | APES on QMNIST · QMNIST, Uniform2 | central user-level privacy εᵘᶜ: 57.6 -> 25.6 | Helped |
| Add post-sparsification to APES (ablation) | APES on QMNIST · QMNIST, Uniform2 | accuracy: 79.67% -> 78.14% | Hurt |
| Use post-sparsification instead of random-sparsification (ablation) | S-APES on QMNIST · QMNIST, Uniform2 | accuracy | Helped |
| Increase the post-sparsification ratio b/d (ablation) | S-APES on QMNIST · QMNIST, Uniform2 | accuracy | Hurt |
| Use Clip-Laplace instead of classic Laplace perturbation (ablation) | APES on QMNIST · QMNIST | accuracy | Mixed |
| Use Clip-Laplace instead of classic Laplace perturbation (ablation) | APES on QMNIST · QMNIST | perturbation variance | Helped |
| Increase the clip bound C (ablation) | Clip-Laplace in APES · QMNIST | accuracy | Mixed |
| Shuffle more datapoints | APES privacy amplification · Privacy amplification evaluation | central privacy εᶜ | Helped |
Closest papers by meaning
- A Generalized Shuffle Framework for Privacy Amplification: Strengthening Privacy Guarantees and Enhancing Utility (AAAI 2024 · similarity 0.91)
- Leveraging Randomness in Model and Data Partitioning for Privacy Amplification (ICML 2025 · similarity 0.89)
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy (NeurIPS 2025 · similarity 0.88)
- Private Model Personalization Revisited (ICML 2025 · similarity 0.88)
- Sketched Gaussian Mechanism for Private Federated Learning (NeurIPS 2025 · similarity 0.88)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.88)
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.