Research map / Federated learning and privacy / Differential privacy
Private Federated Learning with Autotuned Compression
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz, Sewoong Oh
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 |
|---|---|---|---|
| Adapt Norm with c0=0.1 (automatic sketch size) instead of grid-searched Genie compression | Adapt Norm FL · F-EMNIST, Shakespeare, SONWP | validation accuracy and compression rate | Mixed |
| Raise relative compression error constant c0 from 0.1 to 0.25 (ablation) | Adapt Norm FL · F-EMNIST, z=0.1 | compression rate and validation accuracy: accuracy 81.34 -> 78.87; compression 47 -> 101 | Mixed |
| Lower relative compression error constant c0 from 0.1 to 0.01 (ablation) | Adapt Norm FL · F-EMNIST, z=0.1 | compression rate and validation accuracy: accuracy 81.34 -> 82.51; compression 47 -> 5 | Mixed |
| Two Stage method (W=75 uncompressed warm-up rounds, then fixed compression) instead of Adapt Norm (ablation) | Two Stage FL · F-EMNIST, Shakespeare, SONWP | average compression rate | Hurt |
| Adapt Tail (adaptive over log d rounds) used in FL | Adapt Tail FL · federated learning benchmarks | model accuracy | Hurt |
| Adaptive sketch compression (Adapt Norm) vs non-adaptive sketching on F-EMNIST, runtime per round | Adapt Norm FL · F-EMNIST | seconds per round: 3.63s -> 3.69s per round | No clear effect |
Closest papers by meaning
- Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off (ICML 2025 · similarity 0.87)
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.86)
- DictPFL: Efficient and Private Federated Learning on Encrypted Gradients (NeurIPS 2025 · similarity 0.86)
- Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups (NeurIPS 2024 · similarity 0.86)
- Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learning (ICML 2024 · similarity 0.86)
- Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation (ICML 2025 · similarity 0.86)
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.
