Research map / Federated learning and privacy / Communication-efficient FL
Beyond ADMM: A Unified Client-Variance-Reduced Adaptive Federated Learning Framework
Shuai Wang, Yanqing Xu, Zhiguo Wang, Tsung-Hui Chang, Tony Q. S. Quek, Defeng Sun
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 FedVRA instead of FedDyn | Federated learning · CIFAR-10 IID | test accuracy: 74.53 ± 0.14 -> 75.47 ± 0.23 | Improved |
| Use FedVRA instead of FedDyn | Federated learning · CIFAR-10 Non-IID | test accuracy: 71.65 ± 0.41 -> 73.70± 0.54 | Improved |
| Use FedVRA instead of FedDyn | Federated learning · CIFAR-10 Non-IID + HLU | rounds to 60% accuracy: 150 -> 87 | Improved |
| Use FedVRA instead of FedDyn | Federated learning · MNIST Non-IID | test accuracy: 97.74 ± 0.09 -> 98.34 ± 0.06 | Improved |
| Use FedVRA instead of FedDyn | Federated learning · MNIST Non-IID + HLU | rounds to 95% accuracy: 106 -> 49 | Improved |
| Increase aggregation stepsize d_i^r (ablation) | FedVRA · CIFAR-10 and MNIST | convergence speed | Mixed |
| Increase dual stepsize a_i^r appropriately (ablation) | FedVRA · Non-IID CIFAR-10 and MNIST | test performance | Improved |
Closest papers by meaning
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.92)
- Connecting Federated ADMM to Bayes (ICLR 2025 · similarity 0.90)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.89)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.89)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.89)
- TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy Clients (AAAI 2024 · similarity 0.89)
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.
