Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedRAC: Rolling Submodel Allocation for Collaborative Fairness in Federated Learning
Zihui Wang, Yuhang Fu, Mengmeng Du, Zhimin Yuan, Yachen Liu, Weisheng Liao, Kaiyu Wang, Zheng Wang
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 |
|---|---|---|---|
| add dynamic reputation calculation (vs static reputation) (ablation) | FedRAC · SVHN DIR(7.0) | Max test accuracy: 70.56 -> 82.43 | Improved |
| add dynamic reputation calculation (vs static reputation) (ablation) | FedRAC · SVHN DIR(3.0) | Fairness: 95.87 -> 98.00 | Improved |
| add dynamic reputation calculation (vs static reputation) (ablation) | FedRAC · SVHN POW | Fairness: 99.62 -> 99.85 | No clear effect |
| add rolling submodel allocation (vs random submodels) (ablation) | FedRAC · SVHN POW | Max test accuracy: 70.81 -> 79.18 | Improved |
| add rolling submodel allocation (vs random submodels) (ablation) | FedRAC · SVHN POW | Fairness: 95.09 -> 99.85 | Improved |
| add rolling submodel allocation (vs random submodels) (ablation) | FedRAC · SVHN DIR(7.0) | Fairness: 91.58 -> 98.99 | Improved |
| add rolling submodel allocation (vs random submodels) (ablation) | FedRAC · SVHN POW | Rate (BCF): 0.20 -> 1.00 | Improved |
| add dynamic reputation calculation (vs static reputation) (ablation) | FedRAC · SVHN DIR(3.0) | Rate (BCF): 0.70 -> 0.97 | Improved |
| use FedRAC instead of FedAvg | FedRAC · CIFAR10 POW | Fairness: -44.82 -> 99.41 | Improved |
| use FedRAC instead of FedSAC | FedRAC · SVHN CLA | Max test accuracy: 73.28 -> 76.89 | Improved |
| use FedRAC instead of FedAvg | FedRAC · CIFAR10 POW | Max test accuracy: 49.10 -> 49.37 | Improved |
Closest papers by meaning
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning (NeurIPS 2025 · similarity 0.88)
- FedLF: Layer-Wise Fair Federated Learning (AAAI 2024 · similarity 0.87)
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making (ICML 2024 · similarity 0.87)
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.87)
- LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning (AAAI 2025 · similarity 0.87)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.86)
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.
