Sign-Entropy Regularization for Personalized Federated Learning
Personalized Federated Learning (PFL) seeks to train client-specific models across distributed data silos with heterogeneous distributions. We introduce <i>Sign-Entropy Regularization</i> (SER), a novel entropy-based regularization technique that penalizes excessive directional variabili...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/27/6/601 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|