Skip to content

Model Training & Adaptation

Federated learning

Teaching AI across separate devices or organizations while sharing learning changes instead of routinely pooling their original records.

Example

Several sites contribute AI system updates from their local collections of information.

Why people use it

It lets several locations contribute to learning without routinely pooling all their original records.

What you'll hear

“Keep the records local and share learning updates.”

What this means for you

Assess the full privacy and security design, not just where raw data stays.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Does federated learning guarantee privacy by itself?
No. Updates can still expose information without appropriate safeguards.
Can different locations have very different examples?
Yes. Differences between sites can make the combined learning harder.
Does each device have to stay connected continuously?
Not necessarily. The design can organize when participants receive and send updates.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice