SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912128350289920 |
|---|---|
| author | Zhang, Yuxin Lin, Zheng Chen, Zhe Fang, Zihan Zhu, Wenjun Chen, Xianhao Zhao, Jin Gao, Yue |
| author_facet | Zhang, Yuxin Lin, Zheng Chen, Zhe Fang, Zihan Zhu, Wenjun Chen, Xianhao Zhao, Jin Gao, Yue |
| contents | Traditional federated learning (FL) frameworks rely heavily on terrestrial networks, where coverage limitations and increasing bandwidth congestion significantly hinder model convergence. Fortunately, the advancement of low-Earth orbit (LEO) satellite networks offers promising new communication avenues to augment traditional terrestrial FL. Despite this potential, the limited satellite-ground communication bandwidth and the heterogeneous operating environments of ground devices-including variations in data, bandwidth, and computing power-pose substantial challenges for effective and robust satellite-assisted FL. To address these challenges, we propose SatFed, a resource-efficient satellite-assisted heterogeneous FL framework. SatFed implements freshness-based model prioritization queues to optimize the use of highly constrained satellite-ground bandwidth, ensuring the transmission of the most critical models. Additionally, a multigraph is constructed to capture real-time heterogeneous relationships between devices, including data distribution, terrestrial bandwidth, and computing capability. This multigraph enables SatFed to aggregate satellite-transmitted models into peer guidance, enhancing local training in heterogeneous environments. Extensive experiments with real-world LEO satellite networks demonstrate that SatFed achieves superior performance and robustness compared to state-of-the-art benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13503 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework Zhang, Yuxin Lin, Zheng Chen, Zhe Fang, Zihan Zhu, Wenjun Chen, Xianhao Zhao, Jin Gao, Yue Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Traditional federated learning (FL) frameworks rely heavily on terrestrial networks, where coverage limitations and increasing bandwidth congestion significantly hinder model convergence. Fortunately, the advancement of low-Earth orbit (LEO) satellite networks offers promising new communication avenues to augment traditional terrestrial FL. Despite this potential, the limited satellite-ground communication bandwidth and the heterogeneous operating environments of ground devices-including variations in data, bandwidth, and computing power-pose substantial challenges for effective and robust satellite-assisted FL. To address these challenges, we propose SatFed, a resource-efficient satellite-assisted heterogeneous FL framework. SatFed implements freshness-based model prioritization queues to optimize the use of highly constrained satellite-ground bandwidth, ensuring the transmission of the most critical models. Additionally, a multigraph is constructed to capture real-time heterogeneous relationships between devices, including data distribution, terrestrial bandwidth, and computing capability. This multigraph enables SatFed to aggregate satellite-transmitted models into peer guidance, enhancing local training in heterogeneous environments. Extensive experiments with real-world LEO satellite networks demonstrate that SatFed achieves superior performance and robustness compared to state-of-the-art benchmarks. |
| title | SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2409.13503 |