Federated averaging
MethodFederated averaging combines local model updates from participating clients into an updated shared model.
Read
Papers
- Communication-Efficient Learning of Deep Networks from Decentralized Data (opens in a new tab)Proceedings of Machine Learning Research
About this resource
Trains on decentralized client data through repeated local optimization and server aggregation, discussing communication cost and non-IID data.
Where to read: Federated Averaging with local client updates and model aggregation
Checked 2026-10-08
Authority for this purpose: Existing scholarly source independently inspected against this concept; publication category is kept distinct from preprint and instruction.
Destination inspection: Bounded GET; public DNS/IP pinned; redirect-by-redirect validation; destination text inspection required; reviewed destination title, provenance and concept-specific subject
Useful destination; no explanatory claim is asserted from this link.
- Useful scoped source; attaching it does not establish historical priority or independent superiority.
Attached reference
Original reference type: scholarly publication
Original reference verification scope: Bibliographic eligibility only; see scoped relationship evidence.
Reviewed authoritative resource
Where to read: Federated Averaging with local client updates and model aggregation
A first-party destination supports its documented scope; it does not establish independent performance validation or historical priority.
Related concepts
Broader
- Federated learningMethod
Related
Loading discussion…
