Summary

Federated machine learning (FML) is an emerging distributed machine learning paradigm that enables collaborative model training across a large number of distributed datasets while preserving data security. Computationis performed where the data resides, allowing models to be trained locally without exposing or transferring the underlying data.

Recommendation ITU-T F.748.84 provides a functional architecture of the federated machine learning (FML) based service in decentralized environments, including relevant general messages and information flows.