Computationally Efficient Neural Receivers via Axial Self-Attention

Abstract: Deep learning-based neural receivers are redefining physical-layer signal processing for next-generation wireless systems. We propose an axial self-attention transformer neural receiver designed for applicability to 6G and beyond wireless systems, validated through 5G-compliant experimental configurations, that achieves state-of-the-art block error rate (BLER) performance with significantly improved computational efficiency. By factorizing attention operations along temporal and spectral axes, the proposed architecture reduces the quadratic complexity of conventional multi-head self-attention from $O((TF)^2)$ to $O(T^2F+TF^2)$, yielding substantially fewer total floating-point operations and attention matrix multiplications per transformer block compared to global self-attention. Relative to convolutional neural receiver baselines, the axial neural receiver achieves significantly lower computational cost with a fraction of the parameters. Experimental validation under 3GPP Clustered Delay Line (CDL) channels demonstrates consistent performance gains across varying mobility scenarios. Under non-line-of-sight CDL-C conditions, the axial neural receiver consistently outperforms all evaluated receiver architectures, including global self-attention, convolutional neural receivers, and traditional LS-LMMSE at 10\% BLER with reduced computational complexity per inference. At stringent reliability targets of 1\% BLER, the axial receiver maintains robust symbol detection at high user speeds, whereas the traditional LS-LMMSE receiver fails to converge, underscoring its suitability for ultra-reliable low-latency (URLLC) communication in dynamic 6G environments and beyond. These results establish the axial neural receiver as a structured, scalable, and efficient framework for AI-Native 6G RAN systems, enabling deployment in resource-constrained edge environments.