Better Lightweight Network for Free: Codeword Mimic Learning for Massive MIMO CSI feedback

TL;DR

This paper introduces a novel codeword mimic learning method that enhances lightweight neural networks for massive MIMO CSI feedback, improving accuracy without increasing inference costs.

Contribution

The paper proposes a cost-free distillation technique called codeword mimic and a specialized training strategy to improve lightweight feedback network performance.

Findings

Codeword mimic outperforms previous distillation methods

Boosts lightweight network accuracy without extra inference cost

Effective in massive MIMO CSI feedback scenarios

Abstract

The channel state information (CSI) needs to be fed back from the user equipment (UE) to the base station (BS) in frequency division duplexing (FDD) multiple-input multiple-output (MIMO) system. Recently, neural networks are widely applied to CSI compressed feedback since the original overhead is too large for the massive MIMO system. Notably, lightweight feedback networks attract special attention due to their practicality of deployment. However, the feedback accuracy is likely to be harmed by the network compression. In this paper, a cost free distillation technique named codeword mimic (CM) is proposed to train better feedback networks with the practical lightweight encoder. A mimic-explore training strategy with a special distillation scheduler is designed to enhance the CM learning. Experiments show that the proposed CM learning outperforms the previous state-of-the-art feedback distillation method, boosting the performance of the lightweight feedback network without any extra inference cost.