Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911746440036352 |
|---|---|
| author | Azimi-Abarghouyi, Seyed Mohammad Fodor, Viktoria |
| author_facet | Azimi-Abarghouyi, Seyed Mohammad Fodor, Viktoria |
| contents | When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a learning method designed to address these challenges, along with a scalable transmission scheme that efficiently uses a single wireless resource through over-the-air computation. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of interference is minimized through optimized receiver normalizing factors. For this, we model a multi-cluster wireless network using stochastic geometry, and characterize the mean squared error of the aggregation estimations as a function of the network parameters. We show that despite the interference and the data heterogeneity, the proposed scheme achieves high learning accuracy and can significantly outperform the conventional hierarchical algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01442 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity Azimi-Abarghouyi, Seyed Mohammad Fodor, Viktoria Information Theory Artificial Intelligence Machine Learning When implementing hierarchical federated learning over wireless networks, scalability assurance and the ability to handle both interference and device data heterogeneity are crucial. This work introduces a learning method designed to address these challenges, along with a scalable transmission scheme that efficiently uses a single wireless resource through over-the-air computation. To provide resistance against data heterogeneity, we employ gradient aggregations. Meanwhile, the impact of interference is minimized through optimized receiver normalizing factors. For this, we model a multi-cluster wireless network using stochastic geometry, and characterize the mean squared error of the aggregation estimations as a function of the network parameters. We show that despite the interference and the data heterogeneity, the proposed scheme achieves high learning accuracy and can significantly outperform the conventional hierarchical algorithm. |
| title | Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity |
| topic | Information Theory Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2401.01442 |