Transfer Learning Capabilities of Untrained Neural Networks for MIMO CSI Recreation
This addresses the problem of high data requirements for real-world ML deployment in wireless communications, particularly for 5G and beyond, but appears incremental as it builds on existing UNN concepts.
The paper tackles the challenge of needing labeled signals and extensive measurement campaigns for machine learning in wireless communications by proposing untrained neural networks (UNNs) for MIMO channel recreation and low-overhead reporting, showing that transfer learning provides higher channel gain for neighboring users and under-parameterization enables efficient CSI reporting.
Machine learning (ML) applications for wireless communications have gained momentum on the standardization discussions for 5G advanced and beyond. One of the biggest challenges for real world ML deployment is the need for labeled signals and big measurement campaigns. To overcome those problems, we propose the use of untrained neural networks (UNNs) for MIMO channel recreation/estimation and low overhead reporting. The UNNs learn the propagation environment by fitting a few channel measurements and we exploit their learned prior to provide higher channel estimation gains. Moreover, we present a UNN for simultaneous channel recreation for multiple users, or multiple user equipment (UE) positions, in which we have a trade-off between the estimated channel gain and the number of parameters. Our results show that transfer learning techniques are effective in accessing the learned prior on the environment structure as they provide higher channel gain for neighbouring users. Moreover, we indicate how the under-parameterization of UNNs can further enable low-overhead channel state information (CSI) reporting.