FedFrozen: Two-Stage Federated Optimization via Attention Kernel Freezing

ArXi:2605.06446v1 Announce Type: new Federated learning with heterogeneous clients remains a significant challenge for deep learning, primarily due to client drift arising from inconsistent local updates. Existing federated optimization methods typically address this issue through objective-level regularization or update-correction mechanisms. Recent studies, however, suggest that Transformer-based architectures may be inherently robust than conventional models under heterogeneous federated.