发表机构
Pohang University of Science and Technology; Institute of New Media and Communications, Seoul National University; Department of Electrical and Computer Engineering, Seoul National University; Department of Electrical Engineering, Stanford University（浦项科技大学; 首尔大学新媒体与通信研究所; 首尔大学电气与计算机工程系; 斯坦福大学电气工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究无标签信道状态信息的自监督表示学习，提出波束响应对比学习框架BRCL，基于发射端Gram矩阵，结合重建学习实现样本级CSI恢复和波束响应级一致性，实验表明其提高标签效率且性能优于其他预训练方法。
AI 中文摘要
从无标签信道状态信息（CSI）进行自监督表示学习可减少基于学习的多输入多输出（MIMO）系统中的标签和适配开销。现有CSI预训练方法通常使用重建目标或通用增强的对比对，未明确反映与传输相关的信道相似性。本文提出基于发射端Gram矩阵的自监督CSI预训练框架波束响应对比学习（BRCL）。对于信道矩阵\(\mathbf{H}\)，\(\mathbf{R}=\mathbf{H}^{\mathrm{H}}\mathbf{H}\)确定任意单位范数发射波束\(\mathbf{w}\)的接收功率为\(|\mathbf{H}\mathbf{w}|_2^2=\mathbf{w}^{\mathrm{H}}\mathbf{R}\mathbf{w}\)。BRCL将每个CSI样本映射到波束响应轮廓，并使用诱导的软相似性作为对比预训练的无标签关系目标。结合重建学习，BRCL实现样本级CSI恢复和波束响应级一致性，产生无需特定任务标签或手动正样本对的可转移CSI表示。在不同MIMO信道数据集上的实验表明，BRCL提高了标签效率，在波束选择、用户选择和未来波束选择任务中优于基于自动编码器和信道绘图的预训练。
英文摘要
Self-supervised representation learning from unlabeled channel state information (CSI) can reduce labeling and adaptation overhead in learning-based multiple-input multiple-output (MIMO) systems. Existing CSI pretraining methods typically use reconstruction objectives or contrastive pairs from generic augmentations, which do not explicitly reflect transmission-relevant channel similarity. This paper proposes beam-response contrastive learning (BRCL), a self-supervised CSI pretraining framework based on the transmit-side Gram matrix. For a channel matrix $\mathbf{H}$, $\mathbf{R}=\mathbf{H}^{\mathrm{H}}\mathbf{H}$ determines the received power of any unit-norm transmit beam $\mathbf{w}$ as $|\mathbf{H}\mathbf{w}|_2^2=\mathbf{w}^{\mathrm{H}}\mathbf{R}\mathbf{w}$. BRCL maps each CSI sample to a beam-response profile and uses the induced soft similarity as a label-free relational target for contrastive pretraining. Combined with reconstruction learning, BRCL enforces both sample-level CSI recovery and beam-response-level consistency, yielding transferable CSI representations without task-specific labels or manual positive pairs. Experiments on diverse MIMO channel datasets show that BRCL improves label efficiency and outperforms autoencoder- and channel-charting-based pretraining across beam selection, user selection, and future beam selection tasks.
