Dynamic Adaptive Federated Learning for mmWave Sector Selection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915533803225088 |
|---|---|
| author | Pacheco, Lucas Braun, Torsten Chowdhury, Kaushik Rosário, Denis Salehi, Batool Cerqueira, Eduardo |
| author_facet | Pacheco, Lucas Braun, Torsten Chowdhury, Kaushik Rosário, Denis Salehi, Batool Cerqueira, Eduardo |
| contents | Beamforming techniques use massive antenna arrays to formulate narrow Line-of-Sight signal sectors to address the increased signal attenuation in millimeter Wave (mmWave). However, traditional sector selection schemes involve extensive searches for the highest signal-strength sector, introducing extra latency and communication overhead. This paper introduces a dynamic layer-wise and clustering-based federated learning (FL) algorithm for beam sector selection in autonomous vehicle networks called enhanced Dynamic Adaptive FL (eDAFL). The algorithm detects and selects the most important layers of a machine learning model for aggregation in the FL process, significantly reducing network overhead and failure risks. eDAFL also considers intra-cluster and inter-cluster approaches to reduce overfitting and increase the abstraction level. We evaluate eDAFL on a real-world multi-modal dataset, demonstrating improved model accuracy by approximately 6.76% compared to existing methods, while reducing inference time by 84.04% and model size by up to 52.20%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Adaptive Federated Learning for mmWave Sector Selection Pacheco, Lucas Braun, Torsten Chowdhury, Kaushik Rosário, Denis Salehi, Batool Cerqueira, Eduardo Networking and Internet Architecture Beamforming techniques use massive antenna arrays to formulate narrow Line-of-Sight signal sectors to address the increased signal attenuation in millimeter Wave (mmWave). However, traditional sector selection schemes involve extensive searches for the highest signal-strength sector, introducing extra latency and communication overhead. This paper introduces a dynamic layer-wise and clustering-based federated learning (FL) algorithm for beam sector selection in autonomous vehicle networks called enhanced Dynamic Adaptive FL (eDAFL). The algorithm detects and selects the most important layers of a machine learning model for aggregation in the FL process, significantly reducing network overhead and failure risks. eDAFL also considers intra-cluster and inter-cluster approaches to reduce overfitting and increase the abstraction level. We evaluate eDAFL on a real-world multi-modal dataset, demonstrating improved model accuracy by approximately 6.76% compared to existing methods, while reducing inference time by 84.04% and model size by up to 52.20%. |
| title | Dynamic Adaptive Federated Learning for mmWave Sector Selection |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2510.04183 |