Efficient Beamforming Optimization for STAR-RIS-Assisted Communications: A Gradient-Based Meta Learning Approach

TL;DR

The paper tackles the challenging joint beamforming problem in STAR-RIS-assisted MU-MISO networks, which is high-dimensional and nonconvex. It introduces a gradient-based meta-learning (GML) framework that feeds optimization gradients into lightweight neural networks to refine the BS precoding and STAR-RIS amplitude/phase parameters without pre-training. The method reformulates STAR-RIS coefficients into aggregate amplitude and phase, and uses three small networks (PN, AN, TN) within a nested three-layer optimization to achieve near-AO weighted sum-rate performance with significantly reduced computational complexity. Experiments demonstrate fast convergence, near-optimal performance, and up to 10× runtime speedups, highlighting GML’s scalability for large-scale STAR-RIS deployments.

Abstract

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) has emerged as a promising technology to realize full-space coverage and boost spectral efficiency in next-generation wireless networks. Yet, the joint design of the base station precoding matrix as well as the STAR-RIS transmission and reflection coefficient matrices leads to a high-dimensional, strongly nonconvex, and NP-hard optimization problem. Conventional alternating optimization (AO) schemes typically involve repeated large-scale matrix inversion operations, resulting in high computational complexity and poor scalability, while existing deep learning approaches often rely on expensive pre-training and large network models. In this paper, we develop a gradient-based meta learning (GML) framework that directly feeds optimization gradients into lightweight neural networks, thereby removing the need for pre-training and enabling fast adaptation. Specifically, we design dedicated GML-based schemes for both independent-phase and coupled-phase STAR-RIS models, effectively handling their respective amplitude and phase constraints while achieving weighted sum-rate performance very close to that of AO-based benchmarks. Extensive simulations demonstrate that, for both phase models, the proposed methods substantially reduce computational overhead, with complexity growing nearly linearly when the number of BS antennas and STAR-RIS elements grows, and yielding up to 10 times runtime speedup over AO, which confirms the scalability and practicality of the proposed GML method for large-scale STAR-RIS-assisted communications.

Figures (9)

• Figure 1: STAR-RIS-aided MU-MISO system.
• Figure 2: The proposed GML architecture, consisting of three lightweight sub-networks PN, AN, and TN, which update $\bf W$, $\bf A$, and $\bf \Phi$ using their respective WSR gradients sequentially.
• Figure 3: The simulation scenario for STAR-RIS-assisted MU-MISO communications.
• Figure 4: WSR vs. Epoch.
• Figure 5: WSR vs. the number of STAR-RIS elements.