Research map / Federated learning and privacy / Personalized and heterogeneous FL
Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning
Sen Cui, Weishen Pan, Jian Liang, Changshui Zhang, Fei 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 |
|---|---|---|---|
| Tighten client-specific fairness budgets by reducing w from 1.0 to 0.2 | FCFL on eICU LoS prediction · eICU | maximum client disparity: 0.2 -> 0.05 | Improved |
| Tighten client-specific fairness budgets by reducing w from 1.0 to 0.2 | FCFL on eICU LoS prediction · eICU | minimum client utility: 0.62 -> 0.6 | Hurt |
| Use FCFL instead of the reported baselines under ε = 0.05 | Adult income prediction · Adult, race, ε = 0.05 | fairness-constraint satisfaction | Improved |
| Use FCFL instead of the reported baselines under ε = 0.01 | Adult income prediction · Adult, race, ε = 0.01 | fairness-constraint satisfaction | Improved |
| Use FCFL instead of the baselines under the tighter equal fairness budget | FCFL on eICU LoS prediction · eICU, race, ε = 0.05 | client disparity: 0.68 | Improved |
| Optimize the surrogate maximum over all client objectives rather than focusing on only the single worst client | FCFL · Federated learning | client utility consistency | Improved |
Closest papers by meaning
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.91)
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (CVPR 2024 · similarity 0.90)
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning (NeurIPS 2025 · similarity 0.89)
- Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition (ICLR 2024 · similarity 0.89)
- FedLF: Layer-Wise Fair Federated Learning (AAAI 2024 · similarity 0.89)
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making (ICML 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.
