The authors advocate leaving training data distributed on mobile devices and learning a shared model by aggregating locally computed updates, an approach the paper calls Federated Learning.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Communication-Efficient Learning of Deep Networks from Decentralized Data → states its contribution → The authors advocate leaving training data distributed on mobile devices and learning a shared model by aggregating locally computed updates, an approach the paper calls Federated Learning.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.