NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913581502562304 |
|---|---|
| author | Wen, Haifeng Michelusi, Nicolò Simeone, Osvaldo Xing, Hong |
| author_facet | Wen, Haifeng Michelusi, Nicolò Simeone, Osvaldo Xing, Hong |
| contents | Over-the-air federated learning (FL), i.e., AirFL, leverages computing primitively over multiple access channels. A long-standing challenge in AirFL is to achieve coherent signal alignment without relying on expensive channel estimation and feedback. This paper proposes NCAirFL, a CSI-free AirFL scheme based on unbiased non-coherent detection at the edge server. By exploiting binary dithering and a long-term memory based error-compensation mechanism, NCAirFL achieves a convergence rate of order $\mathcal{O}(1/\sqrt{T})$ in terms of the average square norm of the gradient for general non-convex and smooth objectives, where $T$ is the number of communication rounds. Experiments demonstrate the competitive performance of NCAirFL compared to vanilla FL with ideal communications and to coherent transmission-based benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13000 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection Wen, Haifeng Michelusi, Nicolò Simeone, Osvaldo Xing, Hong Information Theory Machine Learning Signal Processing Over-the-air federated learning (FL), i.e., AirFL, leverages computing primitively over multiple access channels. A long-standing challenge in AirFL is to achieve coherent signal alignment without relying on expensive channel estimation and feedback. This paper proposes NCAirFL, a CSI-free AirFL scheme based on unbiased non-coherent detection at the edge server. By exploiting binary dithering and a long-term memory based error-compensation mechanism, NCAirFL achieves a convergence rate of order $\mathcal{O}(1/\sqrt{T})$ in terms of the average square norm of the gradient for general non-convex and smooth objectives, where $T$ is the number of communication rounds. Experiments demonstrate the competitive performance of NCAirFL compared to vanilla FL with ideal communications and to coherent transmission-based benchmarks. |
| title | NCAirFL: CSI-Free Over-the-Air Federated Learning Based on Non-Coherent Detection |
| topic | Information Theory Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2411.13000 |