Meta-Learning Driven Lightweight Phase Shift Compression for IRS-Assisted Wireless Systems

TL;DR

This paper introduces MCRNet, a lightweight meta-learning-based framework for compressing phase shift information in IRS-assisted wireless systems, enabling fast adaptation and real-time operation under dynamic conditions.

Contribution

It proposes a novel meta-learning driven compression network with a depthwise convolutional gating module for efficient, adaptable PSI compression in IRS systems.

Findings

Achieves competitive MSE performance across various compression ratios.

Reduces model size and inference latency significantly.

Demonstrates practical scalability and real-time applicability.

Abstract

The phase shift information (PSI) overhead poses a critical challenge to enabling real-time intelligent reflecting surface (IRS)-assisted wireless systems, particularly under dynamic and resource-constrained conditions. In this paper, we propose a lightweight PSI compression framework, termed meta-learning-driven compression and reconstruction network (MCRNet). By leveraging a few-shot adaptation strategy via model-agnostic meta-learning (MAML), MCRNet enables rapid generalization across diverse IRS configurations with minimal retraining overhead. Furthermore, a novel depthwise convolutional gating (DWCG) module is incorporated into the decoder to achieve adaptive local feature modulation with low computational cost, significantly improving decoding efficiency. Extensive simulations demonstrate that MCRNet achieves competitive normalized mean square error performance compared to state-of-the-art baselines across various compression ratios, while substantially reducing model size and inference latency. These results validate the effectiveness of the proposed asymmetric architecture and highlight the practical scalability and real-time applicability of MCRNet for dynamic IRS-assisted wireless deployments.