METHOD AND SYSTEM FOR SCALABLE AND DECENTRALIZED INCREMENTAL MACHINE LEARNING WHICH PROTECTS DATA PRIVACY

摘要

A computer-implemented method for client-specific federated learning is disclosed applicable in a system including a central server unit and a plurality of client units. The client units are respectively located at different local sites and respectively include local data which is subject to data privacy regulations. In an embodiment, the method includes providing, to one or more of the client units, a toolset, the toolset being configured such that a plurality of different machine learned models can be derived from the toolset at the one or more client units. It further includes receiving, from the one or more client units, one or more machine learned models, the one or more machine learned models being respectively derived from the toolset and trained based and the respective local data by the client units. Finally, the method includes storing the one or more machine learned models in the central server unit.