A Meta-Learning Based Precoder Optimization Framework for Rate-Splitting Multiple Access

TL;DR

This paper introduces a meta-learning framework for optimizing RSMA precoders with partial CSIT, achieving efficient and high-performance solutions that outperform traditional methods especially in large-scale systems.

Contribution

It presents a novel meta-learning approach that directly optimizes RSMA precoders using neural networks, reducing training data needs and computational time.

Findings

Achieves similar ASR to conventional methods in medium-scale scenarios.

Significantly outperforms low complexity precoders in large-scale regimes.

Reduces training time by exploiting neural network overfitting.

Abstract

In this letter, we propose the use of a meta-learning based precoder optimization framework to directly optimize the Rate-Splitting Multiple Access (RSMA) precoders with partial Channel State Information at the Transmitter (CSIT). By exploiting the overfitting of the compact neural network to maximize the explicit Average Sum-Rate (ASR) expression, we effectively bypass the need for any other training data while minimizing the total running time. Numerical results reveal that the meta-learning based solution achieves similar ASR performance to conventional precoder optimization in medium-scale scenarios, and significantly outperforms sub-optimal low complexity precoder algorithms in the large-scale regime.