Research map / Federated learning and privacy / Communication-efficient FL
Faster Adaptive Federated Learning
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 FAFED instead of the strongest listed baseline, FedAMS | CNN federated training · Fashion-MNIST, low heterogeneity | accuracy: 0.8697 -> 0.8816 | Helped |
| Use FAFED instead of the strongest listed baseline, FedAMS | CNN federated training · Fashion-MNIST, medium heterogeneity | accuracy: 0.8615 -> 0.8654 | Helped |
| Use FAFED instead of the strongest listed baseline, STEM | CNN federated training · Fashion-MNIST, high heterogeneity | accuracy: 0.8053 -> 0.8188 | Helped |
| Replace client-specific adaptive learning rates with a shared rate formed by averaging adaptive information across clients | Naive adaptive FedAvg · Heterogeneous cross-silo FL; constructed counterexample | distance from the stationary point | Helped |
| Use momentum-based variance-reduced gradient estimation and synchronized client trackers | FAFED · Non-convex heterogeneous cross-silo FL, ε-stationary point | sample complexity: O\left(\epsilon^{-4}\right) -> \tilde{O} \left(\epsilon^{-3}\right) | Helped |
| Use momentum-based variance-reduced gradient estimation and synchronized client trackers | FAFED · Non-convex heterogeneous cross-silo FL, ε-stationary point | communication complexity: O\left( \epsilon^{-4}\right) -> \tilde{O}\left(\epsilon^{-2}\right) | Helped |
Closest papers by meaning
- Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning (ICML 2025 · similarity 0.88)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.88)
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.87)
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · similarity 0.87)
- Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging (ICML 2025 · similarity 0.87)
- FADAS: Towards Federated Adaptive Asynchronous Optimization (ICML 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.