Research map / Federated learning and privacy / Communication-efficient FL
Breaking the centralized barrier for cross-device federated learning
Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U Stich, Ananda Theertha Suresh
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 Mime (SVRG correction + server optimizer state at each client step) instead of FedAvg, Adam base | Adam base optimizer · EMNIST CNN | accuracy (%): 85.9 -> 86.6 | Improved |
| use MimeAdam instead of FedAvgAdam | Adam base optimizer · Shakespeare | accuracy (%): 18.5 -> 54.1 | Improved |
| use MimeAdam instead of FedAvgAdam | Adam base optimizer · StackOverflow | accuracy (%): 3.2 -> 22.8 | Improved |
| use MimeSGD (SVRG correction) instead of FedAvgSGD | SGD base optimizer · StackOverflow | accuracy (%): 23.8 -> 12.5 | Hurt |
| use MimeAdagrad instead of FedAvgAdagrad | Adagrad base optimizer · StackOverflow | accuracy (%): 24.2 -> 14.7 | Hurt |
| use MimeMom instead of FedAvgMom | momentum base optimizer · Shakespeare | accuracy (%): 55.4 -> 53.6 | Hurt |
| use Mime-style local application of momentum instead of server-only momentum (ablation) | Mime · EMNIST62 MLP, 10 local epochs | accuracy | Improved |
| keep optimizer state fixed globally instead of updating it locally (Loc-Mime) (ablation) | Mime · EMNIST62 MLP, 10 local epochs | accuracy | Improved |
| drop the SVRG correction (MimeLite vs Mime) (ablation) | Mime · EMNIST62 MLP, 10 local epochs | accuracy | No clear effect |
| use Mime/MimeLite instead of FedAvg | SGD+momentum, MLP · EMNIST62 MLP | rounds to converge: about 7x faster | Improved |
| use Mime instead of SCAFFOLD/FedProx | SGD+momentum · EMNIST62 MLP | accuracy | Improved |
Closest papers by meaning
- TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (AAAI 2024 · similarity 0.88)
- Debiasing Federated Learning with Correlated Client Participation (ICLR 2025 · similarity 0.88)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.87)
- Accelerating Federated Learning with Quick Distributed Mean Estimation (ICML 2024 · similarity 0.87)
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.87)
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler (ICLR 2024 · 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.
