LLM Enabled Beam Training for Pinching Antenna Systems (PASS)

TL;DR

This paper introduces an LLM-enabled beam training framework for pinching antenna systems in MIMO communications, significantly reducing overhead and improving beamforming and sum rate performance.

Contribution

It develops a novel LLM-based supervised learning mechanism for environment-adaptive beam training in PASS, applicable to both single-user and multi-user scenarios.

Findings

Achieves over 95% Top-1 accuracy in single-user beam selection.

Improves beamforming gains by 51.92% over conventional methods.

Enhances sum rate by up to 57.14% in multi-user scenarios.

Abstract

To enable intelligent beam training, a large language model (LLM)-enabled beam training framework is proposed for the pinching antenna system (PASS) in downlink multi-user multiple-input multiple-output (MIMO) communications. A novel LLM-based beam training supervised learning mechanism is developed, allowing context-aware and environment-adaptive probing for PASS to reduce overheads. Both single-user and multi-user cases are considered. 1) For single-user case, the LLM-based pinching beamforming codebook generation problem is formulated to maximize the beamforming gain. Then, the optimal transmit beamforming is obtained by maximum ratio transmission (MRT). 2) For multi-user case, a joint codebook generation and beam selection problem is formulated based on the system sum rate under the minimum mean square error (MMSE) transmit beamforming. The training labels for pinching beamforming are constructed by selecting the beam combination that maximizes system performance from each user's Top-S candidate beams. Based on pretrained Generative Pre-trained Transformers (GPTs), the LLM is trained in an end-to-end fashion to minimize the cross-entropy loss. Simulation results demonstrate that: i) For single-user case, the proposed LLM-enabled PASS attains over 95% Top-1 accuracy in beam selection and achieves 51.92% improvements in beamforming gains compared to conventional method. ii) For multi-user case, the proposed LLM-enabled PASS framework significantly outperforms both the LLM-based massive MIMO and conventional PASS beam training, achieving up to 57.14% and 33.33% improvements in sum rate, respectively.