Research map / Federated learning and privacy / Communication-efficient FL
FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning
Check 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 correlation-based active client selection instead of Pow-d | FedAvg · FMNIST 2SPC | communication rounds to 69% target accuracy: 126.6±78.2 -> 94.8±18.4 | Helped |
| Use correlation-based active client selection instead of Pow-d | FedAvg · FMNIST 1SPC | communication rounds to 62% target accuracy: 167.2±72.3 -> 84.0±53.1 | Helped |
| Use correlation-based active client selection instead of Pow-d | FedAvg · FMNIST Dir | communication rounds to 64% target accuracy: 123.0±101.0 -> 68.8±27.5 | Helped |
| Use correlation-based active client selection instead of Pow-d | FedAvg · CIFAR-10 2SPC | communication rounds to 62% target accuracy: 1558.2±227.0 -> 1033.4±123.7 | Helped |
| Use correlation-based active client selection instead of Pow-d | FedAvg · CIFAR-10 1SPC | communication rounds to 36% target accuracy: 1752.2±186.2 -> 1269.2±70.6 | Helped |
| Use correlation-based active client selection instead of Pow-d | FedAvg · CIFAR-10 Dir | communication rounds to 54% target accuracy: 1355.2±151.3 -> 1076.8±262.8 | Helped |
| Increase the GP training interval after warm-up (ablation) | FedCor · FMNIST and CIFAR-10; 2SPC, 1SPC, and Dir | test accuracy and convergence | No clear effect |
| Stop updating the GP after the warm-up phase (ablation) | FedCor · FMNIST and CIFAR-10; 2SPC, 1SPC, and Dir | convergence relative to random selection | Helped |
| Use smaller annealing coefficient β (ablation) | FedCor · FMNIST and CIFAR-10 2SPC | test accuracy | No clear effect |
Closest papers by meaning
- Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning (NeurIPS 2024 · similarity 0.92)
- Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning (AAAI 2025 · similarity 0.89)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.89)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.89)
- Ranking-based Client Imitation Selection for Efficient Federated Learning (ICML 2024 · similarity 0.89)
- FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation (NeurIPS 2026 · similarity 0.88)
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.