<ul><li>Split Federated Learning (SFL) combines federated learning and split learning.</li><li>SFL partitions a neural network at a cut layer, with initial layers on clients and remaining layers on a training server.</li><li>SFL-V1 maintains separate server-side models for each client, while SFL-V2 maintains a single shared model for all clients.</li><li>Cut layer selection significantly affects the performance of SFL-V2, outperforming FedAvg on certain datasets.</li></ul>

The Impact of Cut Layer Selection in Split Federated Learning

Discover more