Research map / Federated learning and privacy / Differential privacy
On Privacy and Personalization in Cross-Silo Federated Learning
Ken Liu, Shengyuan Hu, Steven Wu, Virginia Smith
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 MR-MTL instead of the benchmark methods | Private cross-silo FL · Vehicle, School, GLEAM, and CIFAR-10 | utility | Improved |
| Use MR-MTL instead of local training or FedAvg | Private cross-silo FL · Vehicle, School, and GLEAM | utility | Improved |
| Increase MR-MTL's regularization strength λ under stronger privacy | MR-MTL · Mean estimation | generalization error | Mixed |
| Warm-start MR-MTL with private IFCA clustering, then train within formed clusters | MR-MTL · Rotated & Masked MNIST | test accuracy | Improved |
| Increase silo-specific heterogeneity after warm-starting MR-MTL with IFCA | MR-MTL with IFCA warm-start · Rotated & Masked MNIST | test accuracy | Mixed |
| Use local finetuning after shared federated training rather than training locally throughout | Local finetuning · Private cross-silo FL | utility | No clear effect |
| Run IFCA cluster selection at every round | IFCA · Private cross-silo FL | utility | Hurt |
| Account for Ditto's extra local training iterations under a fixed privacy budget | Ditto · Private cross-silo FL | utility | Hurt |
| Privately tune MR-MTL's λ using a moderate number of trials | MR-MTL · Mean estimation | utility | Hurt |
Closest papers by meaning
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.88)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.88)
- Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses (ICML 2024 · similarity 0.87)
- Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off (ICML 2025 · similarity 0.87)
- Private Model Personalization Revisited (ICML 2025 · similarity 0.87)
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 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.
