FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction
–Neural Information Processing Systems
Federated Dropout) and reduces the gap between model-heterogeneous and model-homogeneous FL, especially under the large-model large-dataset regime.
Neural Information Processing Systems
Feb-11-2026, 16:58:19 GMT
- Country:
- Asia
- China
- Guangdong Province > Shenzhen (0.04)
- Hong Kong (0.04)
- Middle East > Jordan (0.04)
- China
- North America
- Canada > Ontario
- Toronto (0.14)
- United States
- California > San Diego County
- San Diego (0.04)
- Michigan (0.04)
- Ohio (0.04)
- Virginia (0.04)
- California > San Diego County
- Canada > Ontario
- Asia
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Information Technology (0.46)
- Technology: