Mixed-Precision Over-The-Air Federated Learning via Approximated Computing
Guardat en:
| Publicat a: | arXiv.org (Jun 4, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Altres autors: | , |
| Publicat: |
Cornell University Library, arXiv.org
|
| Matèries: | |
| Accés en línia: | Citation/Abstract Full text outside of ProQuest |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3065122851 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3065122851 | ||
| 045 | 0 | |b d20240604 | |
| 100 | 1 | |a Yuan, Jinsheng | |
| 245 | 1 | |a Mixed-Precision Over-The-Air Federated Learning via Approximated Computing | |
| 260 | |b Cornell University Library, arXiv.org |c Jun 4, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a Over-the-Air Federated Learning (OTA-FL) has been extensively investigated as a privacy-preserving distributed learning mechanism. Realistic systems will see FL clients with diverse size, weight, and power configurations. A critical research gap in existing OTA-FL research is the assumption of homogeneous client computational bit precision. Indeed, many clients may exploit approximate computing (AxC) where bit precisions are adjusted for energy and computational efficiency. The dynamic distribution of bit precision updates amongst FL clients poses an open challenge for OTA-FL, as is is incompatible in the wireless modulation superposition space. Here, we propose an AxC-based OTA-FL framework of clients with multiple precisions, demonstrating the following innovations: (i) optimize the quantization-performance trade-off for both server and clients within the constraints of varying edge computing capabilities and learning accuracy requirements, and (ii) develop heterogeneous gradient resolution OTA-FL modulation schemes to ensure compatibility with physical layer OTA aggregation. Our findings indicate that we can design modulation schemes that enable AxC based OTA-FL, which can achieve 50\% faster and smoother server convergence and a performance enhancement for the lowest precision clients compared to a homogeneous precision approach. This demonstrates the great potential of our AxC-based OTA-FL approach in heterogeneous edge computing environments. | |
| 653 | |a Performance enhancement | ||
| 653 | |a Clients | ||
| 653 | |a Servers | ||
| 653 | |a Edge computing | ||
| 653 | |a Federated learning | ||
| 653 | |a Modulation | ||
| 700 | 1 | |a Zhuangkun Wei | |
| 700 | 1 | |a Guo, Weisi | |
| 773 | 0 | |t arXiv.org |g (Jun 4, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3065122851/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2406.03402 |