Lazy Aggregation for Heterogeneous Federated Learning

Lazy Aggregation for Heterogeneous Federated Learning

Federated learning (FL) is a distributed neural network training paradigm with privacy protection. With the premise of ensuring that local data isn’t leaked, multi-device cooperation trains the model and improves its normalization. Unlike centralized training, FL is susceptible to heterogeneous data...

Full description

Bibliographic Details
Main Authors: Gang Xu, De-Lun Kong, Xiu-Bo Chen, Xin Liu
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Applied Sciences
Subjects:
federated learning
heterogeneous data
lazy aggregation
cross-device momentum
Online Access:https://www.mdpi.com/2076-3417/12/17/8515

Internet

https://www.mdpi.com/2076-3417/12/17/8515

Similar Items