Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909098891542528 |
|---|---|
| author | Kim, Taehyeon Kim, Donggyu Yun, Se-Young |
| author_facet | Kim, Taehyeon Kim, Donggyu Yun, Se-Young |
| contents | In the evolving landscape of federated learning (FL), addressing label noise presents unique challenges due to the decentralized and diverse nature of data collection across clients. Traditional centralized learning approaches to mitigate label noise are constrained in FL by privacy concerns and the heterogeneity of client data. This paper revisits early-learning regularization, introducing an innovative strategy, Federated Label-mixture Regularization (FLR). FLR adeptly adapts to FL's complexities by generating new pseudo labels, blending local and global model predictions. This method not only enhances the accuracy of the global model in both i.i.d. and non-i.i.d. settings but also effectively counters the memorization of noisy labels. Demonstrating compatibility with existing label noise and FL techniques, FLR paves the way for improved generalization in FL environments fraught with label inaccuracies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05353 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels Kim, Taehyeon Kim, Donggyu Yun, Se-Young Machine Learning Distributed, Parallel, and Cluster Computing In the evolving landscape of federated learning (FL), addressing label noise presents unique challenges due to the decentralized and diverse nature of data collection across clients. Traditional centralized learning approaches to mitigate label noise are constrained in FL by privacy concerns and the heterogeneity of client data. This paper revisits early-learning regularization, introducing an innovative strategy, Federated Label-mixture Regularization (FLR). FLR adeptly adapts to FL's complexities by generating new pseudo labels, blending local and global model predictions. This method not only enhances the accuracy of the global model in both i.i.d. and non-i.i.d. settings but also effectively counters the memorization of noisy labels. Demonstrating compatibility with existing label noise and FL techniques, FLR paves the way for improved generalization in FL environments fraught with label inaccuracies. |
| title | Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2402.05353 |