Back to Glossary
Federated Learning
連合学習(れんごうがくしゅう)
AdvancedModels & Architecture
A technique where AI models are trained across multiple devices or servers without sharing the raw data, preserving privacy.
Why It Matters
Federated learning enables AI training on sensitive data (medical, financial) while keeping that data private.
Example in Practice
Google's Gboard learning typing patterns across millions of phones without sending keystrokes to Google's servers.