Comparison of federated learning algorithms.

Comparison of federated learning algorithms.

<div><p>Federated Learning supports collaborative model training across distributed clients while keeping sensitive data decentralized. Still, non-independent and identically distributed data pose challenges like unstable convergence and client drift. We propose Federated Normalized Loss...

Full description

Saved in:
Bibliographic Details
Main Author: Duy-Dong Le (22057362) (author)
Other Authors: Tuong-Nguyen Huynh (22057365) (author), Anh-Khoa Tran (22057368) (author), Minh-Son Dao (19658267) (author), Pham The Bao (22057371) (author)
Published: 2025
Subjects:
Cell Biology
Biotechnology
Science Policy
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
stage l1 normalization
robust federated learning
reducing computational complexity
based weighted aggregation
div >< p
remaining effective
point operations
normalized loss
new method
matching state
lower losses
heterogeneous settings
heavy techniques
dataset sizes
client drift
art performance
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items