Modular Hypernetworks for Scalable and Adaptive Deep MIMO Receivers

TL;DR

This paper introduces modular hypernetworks that dynamically adapt the architecture and weights of deep MIMO receivers to changing channel conditions and user configurations, enhancing performance and scalability.

Contribution

It proposes a novel modular hypernetwork framework that enables real-time adaptation of DNN-based MIMO receivers without retraining, addressing the limitations of static architectures.

Findings

Superior error-rate performance in time-varying channels

Rapid adaptation to network variations

Scalability with the number of users

Abstract

Deep neural networks (DNNs) were shown to facilitate the operation of uplink multiple-input multiple-output (MIMO) receivers, with emerging architectures augmenting modules of classic receiver processing. Current designs consider static DNNs, whose architecture is fixed and weights are pre-trained. This induces a notable challenge, as the resulting MIMO receiver is suitable for a given configuration, i.e., channel distribution and number of users, while in practice these parameters change frequently with network variations and users leaving and joining the network. In this work, we tackle this core challenge of DNN-aided MIMO receivers. We build upon the concept of hypernetworks, augmenting the receiver with a pre-trained deep model whose purpose is to update the weights of the DNN-aided receiver upon instantaneous channel variations. We design our hypernetwork to augment modular deep receivers, leveraging their modularity to have the hypernetwork adapt not only the weights, but also the architecture. Our modular hypernetwork leads to a DNN-aided receiver whose architecture and resulting complexity adapts to the number of users, in addition to channel variations, without retraining. Our numerical studies demonstrate superior error-rate performance of modular hypernetworks in time-varying channels compared to static pre-trained receivers, while providing rapid adaptivity and scalability to network variations.