Research map / Federated learning and privacy / Personalized and heterogeneous FL
FairFed: Enabling Group Fairness in Federated Learning
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 fairness-aware aggregation with local reweighting rather than FedAvg | FairFed · Adult (α=0.1) | EOD: -0.174 -> -0.017 | Helped |
| Use fairness-aware aggregation with local reweighting rather than FedAvg | FairFed · COMPAS (α=0.1) | EOD: -0.065 -> -0.057 | Helped |
| Use fairness-aware aggregation with local reweighting rather than local reweighting alone | FairFed · ACSIncome | EOD: -0.062 to -0.050 | Helped |
| Use fairness-aware aggregation with local reweighting rather than FedAvg | FairFed · TILES | EOD: -0.199 to 0.004 | Helped |
| Reduce η from 1.0 to 0.2, giving uniform accuracy more weight (ablation) | FairFed / RW · Adult (α=0.1) | EOD: -0.017 -> -0.058 | Hurt |
| Reduce η from 1.0 to 0.2, giving uniform accuracy more weight (ablation) | FairFed / RW · COMPAS (α=0.1) | EOD: -0.057 -> -0.085 | Hurt |
| Add local debiasing at more participating clients (ablation) | FairFed · Adult | EOD | Helped |
| Use fairness-aware aggregation without any clients performing local debiasing (ablation) | FairFed · Adult | EOD: 40% | Hurt |
| Mix local reweighting and FairBatch across clients (ablation) | FairFed · Adult | EOD: 0.829 | Helped |
| Use FairFed where clients each contain only one sensitive group (ablation) | FairFed / RW · Adult (single group per client) | EOD: 27% | Helped |
Closest papers by meaning
- FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning (NeurIPS 2025 · similarity 0.91)
- Multi-Dimensional Fair Federated Learning (AAAI 2024 · similarity 0.90)
- Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition (ICLR 2024 · similarity 0.89)
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.89)
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (CVPR 2024 · similarity 0.89)
- LoGoFair: Post-Processing for Local and Global Fairness in Federated Learning (AAAI 2025 · 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.