Federated learning – Definition & Meaning

Definition of federated learning

: a machine-learning method in which multiple devices or organizations train a shared model from locally held data and exchange model updates rather than pooling their raw training records in one central location
- The hospitals used federated learning to improve a shared model without moving patient records into one database.
- A phone can calculate a local update for federated learning and send the update for aggregation when it is available.

Origin & history

first known use2016

Google researchers used federated learning in 2016 for a decentralized training approach and described the method in the 2017 paper Communication-Efficient Learning of Deep Networks from Decentralized Data. Federated averaging became a foundational algorithm for combining locally computed model updates.

Test yourself

Which of these is the meaning of federated learning?

Related terms

machine learning a branch of AI in which computers learn patterns from data instead of following rules written… training data the collection of examples, observations, labels, actions, or feedback that a model learns… on-device AI AI that runs directly on a phone, laptop, car, or other device instead of in the cloud, which… data poisoning an attack that inserts, changes, or selectively removes examples in a machine-learning… membership inference attack a privacy attack that tries to determine whether a particular record, person, document, or… gradient descent an optimization method that improves a model step by step by moving its parameters a little in…

Cite this entry

"Federated learning." AI Dictionary, Dadgogo, https://dadgogo.com/dictionary/federated-learning/. Accessed 12 Oct. 2026.