JSSAnet: Theory-Guided Subchannel Partitioning and Joint Spatial Attention for Near-Field Channel Estimation

TL;DR

This paper introduces JSSAnet, a novel near-field channel estimation method for 6G systems that combines theory-guided subchannel partitioning with joint spatial attention, improving accuracy over existing techniques.

Contribution

The paper proposes a theory-guided joint subchannel-spatial-attention network (JSSAnet) that effectively encodes near-field channel nonlinearity and spatial features for enhanced estimation accuracy.

Findings

JSSAnet outperforms existing methods in channel estimation accuracy.

Embedding sparsity information enhances the attention network's performance.

The proposed approach effectively captures nonlinear dependencies across subchannels.

Abstract

The deployment of extremely large-scale antenna array (ELAA) in sixth-generation (6G) communication systems introduces unique challenges for efficient near-field channel estimation. To tackle these issues, this paper presents a theory-guided approach that incorporates angular information into an attention-based estimation framework. A piecewise Fourier representation is proposed to implicitly encode the near-field channel's inherent nonlinearity, enabling the entire channel to be segmented into multiple subchannels, each mapped to the angular domain via the discrete Fourier transform (DFT). Then, we develop a joint subchannel-spatial-attention network (JSSAnet) to extract the spatial features of both intra- and inter-subchannels. To guide theoretically the design of the joint attention mechanism, we derive upper and lower bounds based on approximation criteria and DFT quantization loss mitigation, respectively. Following by both bounds, a JSSA layer of an attention block is constructed to assign independent and adaptive spatial attention weights to each subchannel in parallel. Subsequently, a feed-forward network (FFN) of an attention block further captures and refines the residual nonlinear dependencies across subchannels. Moreover, the proposed JSSA map is linearly computed via element-wise product combining large-kernel convolutions (DLKC), maintaining strong contextual learning capability. Numerical results verify the effectiveness of embedding sparsity information into the attention network and demonstrate JSSAnet achieves superior estimation performance compared with existing methods.