Transfer Learning Capabilities of Untrained Neural Networks for MIMO CSI Recreation

TL;DR

This paper explores the use of untrained neural networks (UNNs) for MIMO channel estimation, demonstrating their ability to learn environment structure with minimal measurements and enabling low-overhead CSI reporting.

Contribution

It introduces a novel application of UNNs for MIMO channel recreation, including multi-user scenarios, and shows how transfer learning enhances performance with fewer parameters.

Findings

UNNs can effectively learn propagation environments from limited measurements.

Transfer learning improves channel estimation for neighboring users.

Under-parameterized UNNs enable low-overhead CSI reporting.

Abstract

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.