跨频段 CSI 重建的基础模型
A Foundation Model for Cross-Band CSI Reconstruction
浏览论文内容
中文总结 AI 辅助
研究多频段低空无线系统中跨频段 CSI 重建问题，提出在公共频谱表示频段、用射频元数据辅助的基础模型，经特定训练，相比基线降低平均归一化均方误差，能转移到未见频段对且在导频有噪声时仍有效。
中文摘要 AI 辅助
在多频段低空无线系统中，获取密集高频信道状态信息（CSI）成本高昂，因为导频资源有限且信道维度随载波频率、带宽和天线阵列大小而变化。我们解决跨频段 CSI 重建问题，即从密集源频段 CSI 和稀疏、有噪声的目标频段导频中恢复密集目标频段 CSI。我们提出一种基础模型，该模型在公共功率 - 角度 - 延迟频谱中表示每个频段，并使用射频元数据作为编码器 - 解码器的辅助条件。该模型使用导频引导的交叉注意力将源频段结构与目标频段导频融合，使一个模型能够处理异构频段对。它通过导频致密化预训练，然后进行有监督的跨频段微调进行训练。在射线追踪、3GPP 和 DeepMIMO 数据集上，该模型比现有最先进的特定对基线平均归一化均方误差降低了 6.1 dB。它还能在未配对微调的情况下转移到两个未见频段对，比完全有监督基线分别实现了 7.5 dB 和 7.1 dB 的增益，并且在目标导频有噪声时仍然有效。
英文摘要
Acquiring dense high-frequency channel state information (CSI) is costly in multi-band low-altitude wireless systems because pilot resources are limited and channel dimensions change with the carrier frequency, bandwidth, and antenna array size. We address cross-band CSI reconstruction, which recovers dense target-band CSI from dense source-band CSI and sparse, noisy target-band pilots. We propose a foundation model that represents every band in a common power-angle-delay spectrum and uses radio-frequency metadata as auxiliary conditioning for an encoder-decoder. The model uses pilot-guided cross-attention to fuse source-band structure with target-band pilot, allowing one model to handle heterogeneous band pairs. It is trained by pilot-densification pretraining followed by supervised cross-band fine-tuning. On ray-tracing, 3GPP, and DeepMIMO datasets, the model lowers average normalized mean-square error by 6.1 dB over the state-of-the-art pair-specific baseline. It also transfers to two unseen pairs without paired fine-tuning, achieving 7.5 and 7.1 dB gains over fully supervised baselines, and remains effective when target pilots are noisy.
