Averaging Is Probably Not the Optimum Way of Aggregating Parameters in Federated Learning

Averaging Is Probably Not the Optimum Way of Aggregating Parameters in Federated Learning

Federated learning is a decentralized topology of deep learning, that trains a shared model through data distributed among each client (like mobile phones, wearable devices), in order to ensure data privacy by avoiding raw data exposed in data center (server). After each client computes a new model...

Full description

Bibliographic Details
Main Authors: Peng Xiao, Samuel Cheng, Vladimir Stankovic, Dejan Vukobratovic
Format: Article
Language:English
Published: MDPI AG 2020-03-01
Series:Entropy
Subjects:
federated learning
decentralized learning
averaging
mutual information
correlation
Online Access:https://www.mdpi.com/1099-4300/22/3/314

Internet

https://www.mdpi.com/1099-4300/22/3/314

Similar Items