A High-Performance Federated Learning Aggregation Algorithm Based on Learning Rate Adjustment and Client Sampling
Federated learning is a distributed learning framework designed to protect user privacy, widely applied across various domains. However, existing federated learning algorithms face challenges, including slow convergence, significant loss fluctuations during aggregation, and imbalanced client samplin...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Format: | Artigo |
| Sprog: | Inglês |
| Udgivet: |
MDPI AG
2023-10-01
|
| Serier: | Mathematics |
| Fag: | |
| Online adgang: | https://www.mdpi.com/2227-7390/11/20/4344 |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
