Research map / Federated learning and privacy / Communication-efficient FL
Fairness in Federated Learning via Core-Stability
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 CoreFed instead of FedAvg | Federated learning · Adult | U(Average): 1.61 -> 1.68 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · Adult | U(Multi): 2.91 -> 3.61 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · MNIST | U(Average): 0.52 -> 0.56 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · MNIST | U(Multi): 0.091 -> 0.13 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · CIFAR-10 | U(Average): 0.84 -> 0.93 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · CIFAR-10 | U(Multi): 0.45 -> 0.70 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · CIFAR-10 with VGG-11 | U(Average): 2.35 -> 2.71 | Helped |
| Use CoreFed instead of FedAvg | Federated learning · CIFAR-10 with VGG-11 | U(Multi): 2.89 -> 17.15 | Helped |
| Use CoreFed instead of FedAvg | Federated learning with noisy-client data · CIFAR-10 with noisy agents | U(Average): 2.67 -> 2.83 | Helped |
| Use CoreFed instead of FedAvg | Federated learning with noisy-client data · CIFAR-10 with noisy agents | U(Multi): 15.37 -> 20.79 | Helped |
| Use CoreFed instead of FedAvg | Federated learning with 10 agents · CIFAR-10 with 10 agents | U_A: 2.52 -> 2.55 | Helped |
| Use CoreFed instead of FedAvg | Federated learning with 10 agents · CIFAR-10 with 10 agents | U_M: 7084 -> 9173 | Helped |
Closest papers by meaning
- Fair Federated Learning via the Proportional Veto Core (ICML 2024 · similarity 0.94)
- Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors (NeurIPS 2024 · similarity 0.91)
- You Get What You Give: Reciprocally Fair Federated Learning (ICML 2025 · similarity 0.90)
- FairTrade: Achieving Pareto-Optimal Trade-Offs between Balanced Accuracy and Fairness in Federated Learning (AAAI 2024 · similarity 0.89)
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making (ICML 2024 · similarity 0.88)
- Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition (ICLR 2024 · 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.