Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Learning with Bilateral Curation for Partially Class-Disjoint Data
Ziqing Fan, Ruipeng Zhang, Jiangchao Yao, Bo Han, Ya Zhang, Yanfeng 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 global fixed simplex ETF classifier (GE) (ablation) | FedAvg · CIFAR10 full participation | generic accuracy (GA): 64.88 -> 69.70 | Improved |
| add global fixed simplex ETF classifier (GE) (ablation) | FedAvg · CIFAR10 full participation | personal accuracy (PA): 82.50 -> 83.63 | Improved |
| add local adaptation (LA) without global ETF (ablation) | FedAvg · CIFAR10 full participation | generic accuracy (GA): 64.88 -> 63.75 | Hurt |
| add local adaptation (LA) without global ETF (ablation) | FedAvg · SVHN full participation | generic accuracy (GA): 86.36 -> 74.84 | Hurt |
| add local adaptation on top of global ETF (ablation) | FedGE · CIFAR100 partial participation | personal accuracy (PA): 62.67 -> 66.33 | Improved |
| add local adaptation on top of global ETF (ablation) | FedGE · CIFAR10 partial participation | personal accuracy (PA): 77.66 -> 79.95 | Improved |
| add local adaptation on top of global ETF (ablation) | FedGE · CIFAR10 full participation | generic accuracy (GA): 69.70 -> 69.46 | No clear effect |
| add local adaptation on top of global ETF (ablation) | FedGE · Fed-ISIC2019 | personal accuracy (PA): 69.88 -> 79.27 | Improved |
| add global ETF only (ablation) | FedAvg · Fed-ISIC2019 | personal accuracy (PA): 77.27 -> 69.88 | Hurt |
| replace linear distribution matrix Q(x)=x with Q(x)=e^x (ablation) | FedGELA · SVHN Dir(0.1) | generic accuracy (GA): 78.88 -> 78.95 | No clear effect |
| replace Q(x)=x with Q(x)=x^(1/2) (ablation) | FedGELA · SVHN Dir(0.1) | generic accuracy (GA): 78.88 -> 77.18 | Hurt |
| replace FedAvg with FedGELA under pure PCDD | FedAvg · CIFAR10 P50C2 | generic accuracy (GA): 36.22 -> 54.78 | Improved |
Closest papers by meaning
- pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation (CVPR 2025 · similarity 0.87)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.87)
- Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators (AAAI 2024 · similarity 0.86)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.86)
- FedUV: Uniformity and Variance for Heterogeneous Federated Learning (CVPR 2024 · similarity 0.86)
- FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning (CVPR 2024 · 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.
