Zhen-Cheng Fan

FedLSA: Cosine Triggered Reparameterization Augmented by Output Boundary Calibration for Private Federated Low Rank Adaptation

This work proposes FedLSA, a Federated Low-rank Subspace Adaptive update framework, which utilizes the cosine similarity of updates to the low rank coefficient matrix B as an economical proxy for subspace drift, which minimizes overhead on the server through dynamic Singular Value Decomposition (SVD) allocation.