Conference
Open access
Sep 2026
FedGLoRA: Grassmann-Manifold Federated Learning via Dual LoRA for Large EEG Models
FedGLoRA freezes the backbone and communicates only LoRA adapters via a dual-branch design, and aggregates global updates on a Grassmann subspace with a Grassmann-proximal constraint, and uses bidirectional distillation to mitigate imbalance.
Qianyu Chen, Yi-Hao Zhong, Run-Xuan Tang et al.
· Proceedings of the Thirty-Fi... · 0 citations