Research map / Federated learning and privacy / Communication-efficient FL
Adaptive Federated Optimization
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 adaptive server optimization instead of FedAvg | Federated learning · CIFAR-10 | accuracy: 72.8 -> 78.0 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · CIFAR-100 | accuracy: 44.7 -> 52.5 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · EMNIST CR | accuracy: 84.9 -> 85.6 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · Shakespeare | accuracy: 56.9 -> 57.5 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · SO NWP | accuracy: 19.5 -> 25.2 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · SO LR | Recall@5: 30.0 -> 67.1 | Helped |
| Use adaptive server optimization instead of FedAvg | Federated learning · EMNIST AE | MSE: 6.47 -> 0.98 | Helped |
| Use adaptive server optimization instead of FedAvgM | Federated learning · CIFAR-10 | accuracy: 77.4 -> 78.0 | No clear effect |
| Use adaptive server optimization instead of FedAvgM | Federated learning · CIFAR-100 | accuracy: 52.4 -> 52.5 | No clear effect |
| Use adaptive server optimization instead of FedAvgM | Federated learning · EMNIST AE | MSE: 1.65 -> 0.98 | Helped |
| Use adaptive server optimization instead of FedAvgM | Federated learning · Shakespeare | accuracy: 57.3 -> 57.0 | Hurt |
| Use adaptive server optimization instead of FedAvgM | Federated learning · SO NWP | accuracy: 23.8 -> 25.2 | Helped |
Closest papers by meaning
- Efficient Adaptive Federated Optimization (NeurIPS 2025 · similarity 0.92)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.91)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 2024 · similarity 0.91)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.90)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.90)
- A New Theoretical Perspective on Data Heterogeneity in Federated Optimization (ICML 2024 · similarity 0.90)
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.