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...
محفوظ في:
| المؤلفون الرئيسيون: | , , , |
|---|---|
| التنسيق: | Artigo |
| اللغة: | Inglês |
| منشور في: |
MDPI AG
2023-10-01
|
| سلاسل: | Mathematics |
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://www.mdpi.com/2227-7390/11/20/4344 |
| الوسوم: |
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|