FedENLC: An End-to-End Noisy Label Correction Framework in Federated Learning
In this paper, we propose FedENLC, an end-to-end noisy label correction model that performs model training and label correction simultaneously to fundamentally mitigate the label noise problem of federated learning (FL). FedENLC consists of two stages. In the first stage, the proposed model employs...
Збережено в:
| Автори: | , |
|---|---|
| Формат: | Artigo |
| Мова: | Inglês |
| Опубліковано: |
MDPI AG
2026-01-01
|
| Серія: | Mathematics |
| Предмети: | |
| Онлайн доступ: | https://www.mdpi.com/2227-7390/14/2/290 |
| Теги: |
Немає тегів, Будьте першим, хто поставить тег для цього запису!
|