MambaNet: Mamba-assisted Channel Estimation Neural Network With Attention Mechanism

TL;DR

MambaNet introduces a Mamba-assisted neural network with attention for efficient, high-performance channel estimation in OFDM systems, especially with many subcarriers, reducing complexity and improving accuracy.

Contribution

This work presents a novel MambaNet framework integrating self-attention and bidirectional selective scan for enhanced large-scale subcarrier channel estimation.

Findings

Outperforms baseline neural networks in channel estimation accuracy.

Uses fewer parameters than transformer-based models.

Exhibits lower space complexity while maintaining high performance.

Abstract

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.