The Gaussian-Head OFL Family: One-Shot Federated Learning from Client Global Statistics

ArXi:2602.01186v2 Announce Type: replace-cross Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high communication costs and privacy risks from repeated model transmissions. In contrast, one-shot federated learning (OFL) alleviates these limitations by reducing communication to a single round, thereby lowering overhead and enhancing practical deployability.