Metasurfaces-Integrated Wireless Neural Networks for Lightweight Over-The-Air Edge Inference

TL;DR

This paper proposes Metasurfaces-Integrated Neural Networks (MINNs), a novel physical-layer deep learning framework using metasurfaces and MIMO channels to enable low-power, over-the-air edge inference in future wireless networks.

Contribution

It introduces a new hardware-software integrated neural network architecture leveraging metasurfaces and wireless channels for efficient edge inference, reducing power consumption compared to digital methods.

Findings

MINNs achieve performance comparable to digital DNNs

Significant power savings demonstrated in prototype applications

Flexible computation offloading in the physical layer

Abstract

The upcoming sixth Generation (6G) of wireless networks envisions ultra-low latency and energy efficient Edge Inference (EI) for diverse Internet of Things (IoT) applications. However, traditional digital hardware for machine learning is power intensive, motivating the need for alternative computation paradigms. Over-The-Air (OTA) computation is regarded as an emerging transformative approach assigning the wireless channel to actively perform computational tasks. This article introduces the concept of Metasurfaces-Integrated Neural Networks (MINNs), a physical-layer-enabled deep learning framework that leverages programmable multi-layer metasurface structures and Multiple-Input Multiple-Output (MIMO) channels to realize computational layers in the wave propagation domain. The MINN system is conceptualized as three modules: Encoder, Channel (uncontrollable propagation features and metasurfaces), and Decoder. The first and last modules, realized respectively at the multi-antenna transmitter and receiver, consist of conventional digital or purposely designed analog Deep Neural Network (DNN) layers, and the metasurfaces responses of the Channel module are optimized alongside all modules as trainable weights. This architecture enables computation offloading into the end-to-end physical layer, flexibly among its constituent modules, achieving performance comparable to fully digital DNNs while significantly reducing power consumption. The training of the MINN framework, two representative variations, and performance results for indicative applications are presented, highlighting the potential of MINNs as a lightweight and sustainable solution for future EI-enabled wireless systems. The article is concluded with a list of open challenges and promising research directions.