Deep-Unfolding for Next-Generation Transceivers

TL;DR

This paper reviews the application of deep-unfolding techniques, combining iterative algorithms and deep learning, for designing next-generation MIMO transceivers to meet future wireless network demands.

Contribution

It provides a comprehensive overview of deep-unfolding frameworks and recent advancements in their application to advanced transceiver design for wireless communications.

Findings

Deep-unfolding effectively reduces computational complexity.

It bridges the gap between iterative algorithms and deep learning.

Open issues for future research are identified.

Abstract

The stringent performance requirements of future wireless networks, such as ultra-high data rates, extremely high reliability and low latency, are spurring worldwide studies on defining the next-generation multiple-input multiple-output (MIMO) transceivers. For the design of advanced transceivers in wireless communications, optimization approaches often leading to iterative algorithms have achieved great success for MIMO transceivers. However, these algorithms generally require a large number of iterations to converge, which entails considerable computational complexity and often requires fine-tuning of various parameters. With the development of deep learning, approximating the iterative algorithms with deep neural networks (DNNs) can significantly reduce the computational time. However, DNNs typically lead to black-box solvers, which requires amounts of data and extensive training time. To further overcome these challenges, deep-unfolding has emerged which incorporates the benefits of both deep learning and iterative algorithms, by unfolding the iterative algorithm into a layer-wise structure analogous to DNNs. In this article, we first go through the framework of deep-unfolding for transceiver design with matrix parameters and its recent advancements. Then, some endeavors in applying deep-unfolding approaches in next-generation advanced transceiver design are presented. Moreover, some open issues for future research are highlighted.