GPASS: Deep Learning for Beamforming in Pinching-Antenna Systems (PASS)
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_ | 1866910810971832320 |
|---|---|
| author | Guo, Jia Liu, Yuanwei Nallanathan, Arumugam |
| author_facet | Guo, Jia Liu, Yuanwei Nallanathan, Arumugam |
| contents | A novel GPASS architecture is proposed for jointly learning pinching beamforming and transmit beamforming in pinching antenna systems (PASS). The GPASS is with a staged architecture, where the positions of pinching antennas are first learned by a sub-GNN. Then, the transmit beamforming is learned by another sub-GNN based on the antenna positions. The sub-GNNs are incorporated with the permutation property of the beamforming policy, which helps improve the learning performance. The optimal solution structure of transmit beamforming is also leveraged to simplify the mappings to be learned. Numerical results demonstrate that the proposed architecture can achieve a higher SE than a heuristic baseline method with low inference complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GPASS: Deep Learning for Beamforming in Pinching-Antenna Systems (PASS) Guo, Jia Liu, Yuanwei Nallanathan, Arumugam Signal Processing A novel GPASS architecture is proposed for jointly learning pinching beamforming and transmit beamforming in pinching antenna systems (PASS). The GPASS is with a staged architecture, where the positions of pinching antennas are first learned by a sub-GNN. Then, the transmit beamforming is learned by another sub-GNN based on the antenna positions. The sub-GNNs are incorporated with the permutation property of the beamforming policy, which helps improve the learning performance. The optimal solution structure of transmit beamforming is also leveraged to simplify the mappings to be learned. Numerical results demonstrate that the proposed architecture can achieve a higher SE than a heuristic baseline method with low inference complexity. |
| title | GPASS: Deep Learning for Beamforming in Pinching-Antenna Systems (PASS) |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2502.01438 |