Federated Learning

Federated learning trains across distributed devices or organizations. Each federated client trains locally without sending raw data, and model aggregation combines the resulting updates into a shared model.

Japanese terms

1. Federated learning — 連合学習れんごうがくしゅう: Distributed learning in which participants train locally and share model updates rather than raw data.
2. Federated client — 連合れんごうクライアント: A participating device or organization that performs local training in federated learning.
3. Model aggregation — モデル集約しゅうやく: The process of combining model updates received from multiple federated clients.

Related topics

Federated learning is a distributed approach within machine learning and is often motivated by privacy, governance, or data-locality requirements.