FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settings

ArXi:2605.05553v1 Announce Type: new Federated learning (FL) operates in heterogeneous environments, where variations in data distributions and asymmetric model design often result in negative transfer. While federated knowledge distillation (FKD) avoids direct model parameter sharing, existing methods typically rely on public datasets or assume that transferred knowledge is uniformly reliable, which limits their robustness in practice.