Hierarchical Federated ADMM
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929518275461120 |
|---|---|
| author | Azimi-Abarghouyi, Seyed Mohammad Bastianello, Nicola Johansson, Karl H. Fodor, Viktoria |
| author_facet | Azimi-Abarghouyi, Seyed Mohammad Bastianello, Nicola Johansson, Karl H. Fodor, Viktoria |
| contents | In this paper, we depart from the widely-used gradient descent-based hierarchical federated learning (FL) algorithms to develop a novel hierarchical FL framework based on the alternating direction method of multipliers (ADMM). Within this framework, we propose two novel FL algorithms, which both use ADMM in the top layer: one that employs ADMM in the lower layer and another that uses the conventional gradient descent-based approach. The proposed framework enhances privacy, and experiments demonstrate the superiority of the proposed algorithms compared to the conventional algorithms in terms of learning convergence and accuracy. Additionally, gradient descent on the lower layer performs well even if the number of local steps is very limited, while ADMM on both layers lead to better performance otherwise. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18796 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hierarchical Federated ADMM Azimi-Abarghouyi, Seyed Mohammad Bastianello, Nicola Johansson, Karl H. Fodor, Viktoria Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Information Theory Systems and Control In this paper, we depart from the widely-used gradient descent-based hierarchical federated learning (FL) algorithms to develop a novel hierarchical FL framework based on the alternating direction method of multipliers (ADMM). Within this framework, we propose two novel FL algorithms, which both use ADMM in the top layer: one that employs ADMM in the lower layer and another that uses the conventional gradient descent-based approach. The proposed framework enhances privacy, and experiments demonstrate the superiority of the proposed algorithms compared to the conventional algorithms in terms of learning convergence and accuracy. Additionally, gradient descent on the lower layer performs well even if the number of local steps is very limited, while ADMM on both layers lead to better performance otherwise. |
| title | Hierarchical Federated ADMM |
| topic | Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Information Theory Systems and Control |
| url | https://arxiv.org/abs/2409.18796 |