AI 中文总结
针对XL-MIMO的SVD延迟瓶颈，提出SVDNet神经算子，通过单次前向传播生成波束成形所需的低秩因子，在单流传输中性能接近精确SVD，多流和速率优于基线，可扩展至512×512规模。
AI 中文摘要
奇异值分解（SVD）是多输入多输出（MIMO）波束成形中的核心操作，但标准SVD算法的立方复杂度会在阵列尺寸扩展到极大规模时成为主要的延迟瓶颈。本文提出一种完全学习型的神经算子，它无需显式计算SVD，而是直接将信道矩阵映射到截断低秩因子，用于预编码器和组合器设计。与迭代数值求解器和算法展开网络不同，所提出的感知结构模型SVDNet在推理阶段通过单次前向传播生成这些因子，将每个实例的分解成本转移到离线训练中。该模型还包含轻量约束，用于强制波束成形所需的基本代数性质，例如奇异向量的半酉性和非负奇异值，而无需调用矩阵分解核。对矩阵尺寸高达512×512的超大规模MIMO信道进行的实验表明，所提方法在单流传输中实现了接近基于精确SVD的波束成形的频谱效率，并且在多流和速率上始终优于代表性的学习型基线，显示出适用于低延迟无线处理的良好可扩展性。
英文摘要
Singular value decomposition (SVD) is a core operation in multiple-input multiple-output (MIMO) beamforming, but the cubic complexity of standard SVD routines can lead to a major latency bottleneck as array dimensions scale to extremely large sizes. This paper presents a fully learned neural operator that avoids explicit SVD computation by directly mapping channel matrices to truncated low-rank factors for precoder and combiner design. In contrast to iterative numerical solvers and algorithm-unrolled networks, the proposed structure-aware model, termed SVDNet, produces these factors in a single forward pass at inference, shifting the per-instance decomposition cost to offline training. The model also includes lightweight constraints to enforce basic algebraic properties required by beamforming, such as semi-unitarity of the singular vectors and nonnegative singular values, without invoking matrix factorization kernels. Experiments on extremely large-scale MIMO channels with matrix dimensions up to 512*512 show that the proposed approach achieves spectral efficiency close to exact SVD-based beamforming in single-stream transmission and consistently improves multi-stream sum-rate over representative learned baselines, indicating good scalability for low-latency wireless processing.
CommentsAccepted for presentation at the 2026 IEEE 103rd Vehicular Technology Conference (VTC2026-Spring)
