WEIGHTED AVERAGE FEDERATED LEARNING BASED ON NEURAL NETWORK TRAINING LOSS

WEIGHTED AVERAGE FEDERATED LEARNING BASED ON NEURAL NETWORK TRAINING LOSS

A method of wireless communication by a user equipment (UE) includes computing updates to an artificial neural network as part of an epoch of a federated learning process. The updates include gradients or updated model parameters. The method also includes recording a training loss observed while tra...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yoo, Taesang, BALEVI, Eren
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
WIRELESS COMMUNICATIONS NETWORKS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A method of wireless communication by a user equipment (UE) includes computing updates to an artificial neural network as part of an epoch of a federated learning process. The updates include gradients or updated model parameters. The method also includes recording a training loss observed while training the artificial neural network at the epoch of the federated learning process. The method further includes transmitting the updates to a federated learning server that is configured to aggregate the gradients based on the training loss.