Research map / Federated learning and privacy / Personalized and heterogeneous FL
OursFed: Provable Group Fairness-Aware Federated Learning Against Distrust and Fragility
Yun Xin, Jianfeng Lu, Gang Li, Shuqin Cao, Guanghui Wen, Kehao 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 |
|---|---|---|---|
| aggregate with group-fairness-aware weights and contract-based data contribution (OursFed) versus FedAvg | OursFed · COMPAS | RDP (group bias): 0.24±0.04 -> 0.12±0.03 | Improved |
| add group-fairness weighting and contract to data-contribution-only aggregation (FedAvg-W) | OursFed · Adult | RDP (group bias): 0.16±0.01 -> 0.12±0.01 | Improved |
| consider fairness only without data contribution (OGF) versus OursFed | OGF · COMPAS | accuracy: 0.80±0.04 -> 0.60±0.01 | Hurt |
| add fairness handling to FedAvg-W on COMPAS | OursFed · COMPAS | accuracy: 0.84±0.04 -> 0.80±0.04 | Hurt |
| increase emphasis on GF via trade-off knob lambda (ablation) | OursFed · COMPAS and Adult | accuracy vs GF | Mixed |
| replace DP with robust demographic parity (RDP) under perturbation on output scores (ablation) | GF estimation · Synthetic fragility | GF estimation bias | Improved |
| replace DP with RDP under perturbation on sensitive attribute (ablation) | GF estimation · Synthetic fragility | GF estimation bias | Improved |
| use privacy pair-based contract so high-GF low-cost clients contribute more data | OursFed · Synthetic distrust | data contribution and reward | Improved |
Closest papers by meaning
- 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)
- Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors (NeurIPS 2024 · similarity 0.88)
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.87)
- Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity (CVPR 2024 · similarity 0.87)
- Multi-Dimensional Fair Federated Learning (AAAI 2024 · similarity 0.87)
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.
