输入相关的监督噪声限制了OTA训练对学习型接收机的益处
Input-Correlated Supervision Noise Limits the Benefits of OTA Training for Learned Receivers
AI总结：
该研究针对5.88 GHz环境，用混合数据训练学习型接收机，发现OTA训练对端到端接收机和信道估计器的影响存在不对称性，为两类模型的OTA训练提供了指导。
AI中文摘要：
尽管学习型无线接收机通常使用合成数据进行研究，但用于训练的空中（OTA）测量的影响仍不明确。我们开展了一项5.88 GHz的测量活动，使用类5G/6G的正交频分复用（OFDM）系统，覆盖不同环境和移动性条件，并用实测数据与合成数据的混合数据训练了一个神经信道估计器和一个容量匹配的端到端神经接收机。增加OTA数据占比时，发现了一个根本性的不对称性：实测数据持续提升端到端接收机的性能，而信道估计器的性能在中间占比时达到峰值，使用全实测数据训练时会下降。我们证明这种差异源于监督目标：OTA信道标签来自含噪的接收信号，因此包含与接收机输入相关的监督误差，而通过循环冗余校验（CRC）验证的解码比特提供了几乎无误差的监督。一项受控去噪实验证实，是这种相关性而非有限的数据多样性导致了性能下降。这些结果为使用OTA数据训练学习型接收机提供了实用指导：端到端接收机从全实测训练中获益，而信道估计器则从适度的OTA占比中获益，但需要提升标签质量（例如通过去噪）以释放进一步的增益。
英文摘要：
While learned wireless receivers are typically studied using synthetic data, the impact of over-the-air (OTA) measurements for training remains unclear. We conducted a 5.88 GHz measurement campaign with a 5G/6G-like orthogonal frequency-division multiplexing (OFDM) system across diverse environments and mobility conditions, and trained a neural channel estimator and a capacity-matched end-to-end neural receiver using mixtures of measured and synthetic data. Increasing the OTA fraction revealed a fundamental asymmetry: measured data consistently improved the end-to-end receiver, whereas the channel estimator peaked at an intermediate fraction and degraded with fully measured training. We showed that this difference arises from the supervision target: OTA channel labels are derived from noisy received signals and therefore contain supervision errors correlated with the receiver input, whereas decoded bits validated by a cyclic redundancy check (CRC) provide effectively error-free supervision. A controlled denoising experiment confirmed that this correlation, rather than limited data diversity, caused the degradation. These results provide practical guidance for training learned receivers with OTA data: end-to-end receivers benefit from fully measured training, whereas channel estimators benefit from moderate OTA fractions but require improved label quality, e.g. via denoising, to unlock further gains.
