Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Yuhang, Lu, Yang, Chen, Wei, Ai, Bo, Ding, Zhiguo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.11056
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910280512962560
author Li, Yuhang
Lu, Yang
Chen, Wei
Ai, Bo
Ding, Zhiguo
author_facet Li, Yuhang
Lu, Yang
Chen, Wei
Ai, Bo
Ding, Zhiguo
contents Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications primarily focus on fine-tuning pre-trained large language models (LLMs) for specific tasks. This paper investigates the large-scale AI model designed for beamforming optimization to adapt and generalize to diverse tasks defined by system utilities and scales. We propose a novel framework based on bidirectional encoder representations from transformers (BERT), termed BERT4beam. We aim to formulate the beamforming optimization problem as a token-level sequence learning task, perform tokenization of the channel state information, construct the BERT model, and conduct task-specific pre-training and fine-tuning strategies. Based on the framework, we propose two BERT-based approaches for single-task and multi-task beamforming optimization, respectively. Both approaches are generalizable for varying user scales. Moreover, the former can adapt to varying system utilities and antenna configurations by re-configuring the input and output module of the BERT model, while the latter, termed UBERT, can directly generalize to diverse tasks, due to a finer-grained tokenization strategy. Extensive simulation results demonstrate that the two proposed approaches can achieve near-optimal performance and outperform existing AI models across various beamforming optimization tasks, showcasing strong adaptability and generalizability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_11056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization
Li, Yuhang
Lu, Yang
Chen, Wei
Ai, Bo
Ding, Zhiguo
Systems and Control
Machine Learning
Artificial intelligence (AI) is anticipated to emerge as a pivotal enabler for the forthcoming sixth-generation (6G) wireless communication systems. However, current research efforts regarding large AI models for wireless communications primarily focus on fine-tuning pre-trained large language models (LLMs) for specific tasks. This paper investigates the large-scale AI model designed for beamforming optimization to adapt and generalize to diverse tasks defined by system utilities and scales. We propose a novel framework based on bidirectional encoder representations from transformers (BERT), termed BERT4beam. We aim to formulate the beamforming optimization problem as a token-level sequence learning task, perform tokenization of the channel state information, construct the BERT model, and conduct task-specific pre-training and fine-tuning strategies. Based on the framework, we propose two BERT-based approaches for single-task and multi-task beamforming optimization, respectively. Both approaches are generalizable for varying user scales. Moreover, the former can adapt to varying system utilities and antenna configurations by re-configuring the input and output module of the BERT model, while the latter, termed UBERT, can directly generalize to diverse tasks, due to a finer-grained tokenization strategy. Extensive simulation results demonstrate that the two proposed approaches can achieve near-optimal performance and outperform existing AI models across various beamforming optimization tasks, showcasing strong adaptability and generalizability.
title BERT4beam: Large AI Model Enabled Generalized Beamforming Optimization
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2509.11056