FedTeas: Federated Learning via Teacher Distillation and Sharpness-Aware Minimization

Data heterogeneity remains a central challenge in Federated Learning (FL), inducing client drift and often steering optimization toward sharp solutions with poor generalization. While Sharpness-Aware Minimization (SAM) can improve flatness and robustness, locally computed SAM perturbations may become misaligned with the global objective under heterogeneous data. To address this, we introduce FedTeas, a family of three methods: vanilla FedTeas, FedTeasC, and FedTeasM that use global knowledge distillation (KD) as directional guidance for local sharpness-aware optimization. By aligning local perturbations with global predictive knowledge, FedTeas mitigates client drift and yields more consistent, robust global models across communication rounds. Rather than applying KD as a conventional parameter-wise regularizer, FedTeas injects distillation gradients directly into the SAM perturbation step, aligning local perturbations with global predictive knowledge. We prove that vanilla FedTeas retains the $O(1/\sqrt{T})$ convergence rate of FedSAM (seminal approach adapting SAM to FL), while the remaining family members preserve the convergence guarantees of their corresponding optimization frameworks. We establish a $C_{\Omega }$-conditioned generalization bound that characterizes the impact of KD-guided perturbation directions on federated generalization. Extensive experiments across heterogeneous federated benchmarks show that FedTeas consistently improves accuracy, robustness, and generalization over state-of-the-art federated optimization and sharpness-aware baselines. Code is available at https://anonymous.4open.science/r/FedTeas-17D1.