Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.04730 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909677995950080 |
|---|---|
| author | Gansekoele, Arwin Bhulai, Sandjai Hoogendoorn, Mark van der Mei, Rob |
| author_facet | Gansekoele, Arwin Bhulai, Sandjai Hoogendoorn, Mark van der Mei, Rob |
| contents | In the era of telecommunications, the increasing demand for complex and specialized communication systems has led to a focus on improving physical layer communications. Artificial intelligence (AI) has emerged as a promising solution avenue for doing so. Deep neural receivers have already shown significant promise in improving the performance of communications systems. However, a major challenge lies in developing deep neural receivers that match the energy efficiency and speed of traditional receivers. This work investigates the incorporation of inductive biases in the physical layer using group-equivariant deep learning to improve the parameter efficiency of deep neural receivers. We do so by constructing a deep neural receiver that is equivariant with respect to the phase of arrival. We show that the inclusion of relative phase equivariance significantly reduces the error rate of deep neural receivers at similar model sizes. Thus, we show the potential of group-equivariant deep learning in the domain of physical layer communications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04730 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Relative Phase Equivariant Deep Neural Systems for Physical Layer Communications Gansekoele, Arwin Bhulai, Sandjai Hoogendoorn, Mark van der Mei, Rob Information Theory Networking and Internet Architecture In the era of telecommunications, the increasing demand for complex and specialized communication systems has led to a focus on improving physical layer communications. Artificial intelligence (AI) has emerged as a promising solution avenue for doing so. Deep neural receivers have already shown significant promise in improving the performance of communications systems. However, a major challenge lies in developing deep neural receivers that match the energy efficiency and speed of traditional receivers. This work investigates the incorporation of inductive biases in the physical layer using group-equivariant deep learning to improve the parameter efficiency of deep neural receivers. We do so by constructing a deep neural receiver that is equivariant with respect to the phase of arrival. We show that the inclusion of relative phase equivariance significantly reduces the error rate of deep neural receivers at similar model sizes. Thus, we show the potential of group-equivariant deep learning in the domain of physical layer communications. |
| title | Relative Phase Equivariant Deep Neural Systems for Physical Layer Communications |
| topic | Information Theory Networking and Internet Architecture |
| url | https://arxiv.org/abs/2501.04730 |