FP-ANeT: A Fixed-Point Attention Network for Hybrid-Field THz Ultra-massive MIMO Channel Estimation

TL;DR

This paper introduces FP-ANet, a novel fixed-point attention network that improves THz UM-MIMO channel estimation by exploiting channel sparsity and combining fixed-point theory with dual-attention mechanisms.

Contribution

The paper presents a new model-driven channel estimator that integrates fixed-point theory with dual-attention mechanisms for enhanced THz channel estimation.

Findings

FP-ANet outperforms state-of-the-art methods in accuracy.

Maintains similar computational complexity to existing approaches.

Effectively exploits channel sparsity in the angular-distance domain.

Abstract

Ultra-massive multiple-input multiple-output (UM-MIMO) is a key technology for enabling terahertz (THz) communications in 6G networks, offering high beamforming gain to combat severe path loss. However, the large antenna array expands the near-field region, resulting in a hybrid near- and far-field communication environment. This makes channel estimation significantly more challenging than in conventional networks. To address this issue, we propose a novel attention augmented channel estimator named the fixed-point attention network (FP-ANet), which integrates fixed-point theory with a dual-attention mechanism. By combining a linear and dual-attention residual blocks based non-linear estimator in each iteration, this model-driven approach effectively exploits the sparsity of THz channels in the angular-distance domain, enabling a more precise and physically-grounded channel estimation. Simulation results show that FP-ANet achieves superior channel estimation accuracy compared to state-of-the-art methods while maintaining comparable computational complexity.