MambaNet: Mamba-assisted Channel Estimation Neural Network With Attention Mechanism
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917220239540224 |
|---|---|
| author | Luan, Dianxin Liang, Chengsi Huang, Jie Lin, Zheng Meng, Kaitao Thompson, John Wang, Cheng-Xiang |
| author_facet | Luan, Dianxin Liang, Chengsi Huang, Jie Lin, Zheng Meng, Kaitao Thompson, John Wang, Cheng-Xiang |
| contents | This paper proposes a Mamba-assisted neural network framework incorporating self-attention mechanism to achieve improved channel estimation with low complexity for orthogonal frequency-division multiplexing (OFDM) waveforms, particularly for configurations with a large number of subcarriers. With the integration of customized Mamba architecture, the proposed framework handles large-scale subcarrier channel estimation efficiently while capturing long-distance dependencies among these subcarriers effectively. Unlike conventional Mamba structure, this paper implements a bidirectional selective scan to improve channel estimation performance, because channel gains at different subcarriers are non-causal. Moreover, the proposed framework exhibits relatively lower space complexity than transformer-based neural networks. Simulation results tested on the 3GPP TS 36.101 channel demonstrate that compared to other baseline neural network solutions, the proposed method achieves improved channel estimation performance with a reduced number of tunable parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17108 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MambaNet: Mamba-assisted Channel Estimation Neural Network With Attention Mechanism Luan, Dianxin Liang, Chengsi Huang, Jie Lin, Zheng Meng, Kaitao Thompson, John Wang, Cheng-Xiang Machine Learning Artificial Intelligence Signal Processing This paper proposes a Mamba-assisted neural network framework incorporating self-attention mechanism to achieve improved channel estimation with low complexity for orthogonal frequency-division multiplexing (OFDM) waveforms, particularly for configurations with a large number of subcarriers. With the integration of customized Mamba architecture, the proposed framework handles large-scale subcarrier channel estimation efficiently while capturing long-distance dependencies among these subcarriers effectively. Unlike conventional Mamba structure, this paper implements a bidirectional selective scan to improve channel estimation performance, because channel gains at different subcarriers are non-causal. Moreover, the proposed framework exhibits relatively lower space complexity than transformer-based neural networks. Simulation results tested on the 3GPP TS 36.101 channel demonstrate that compared to other baseline neural network solutions, the proposed method achieves improved channel estimation performance with a reduced number of tunable parameters. |
| title | MambaNet: Mamba-assisted Channel Estimation Neural Network With Attention Mechanism |
| topic | Machine Learning Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2601.17108 |