Federated split learning for sequential data in satellite-terrestrial integrated networks

Weiwei Jiang, Haoyu Han, Yang Zhang, Jianbin Mu

Abstract: Highlights•A split-then-federated learning framework in STINs is proposed for the first time.•A FedSL-LSTM model is proven effective for processing sequential data in STINs.•A case study of electricity theft detection with a real-world dataset is conducted.