arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2503.03054eess.SP
收藏

Federated Learning 遇上 Fluid Antenna:迈向鲁棒且可扩展的边缘智能

Federated Learning Meets Fluid Antenna: Towards Robust and Scalable Edge Intelligence

Sangjun Park, Hyowoon Seo

AI总结:

本文将 fluid antenna systems (FAS) 集成到基于 AirComp 的 federated learning 中,通过自适应天线选择规则缓解信道随机性,提升学习鲁棒性,并经算法与仿真验证了其作为无线 AI 关键使能技术的潜力。

摘要:

Federated learning (FL) 是一种新兴的机器学习范式,在支持未来工业的高级服务与应用方面具有巨大潜力。然而,在无线通信系统中部署时,FL 面临显著的通信开销,这可以通过集成 over-the-air computation (AirComp) 来缓解。尽管具有优势,但由于无线信道的固有随机性,AirComp 会引入学习误差,从而可能降低整体学习性能。为解决此问题,本文探讨了将 fluid antenna systems (FAS) 集成到基于 AirComp 的 FL 中,以增强系统的鲁棒性与效率。Fluid antenna 通过自适应选择天线端口提供动态空间分集,从而缓解信道变化并改善信号聚合。具体而言,我们为配备 fluid antenna 的设备提出了一种天线选择规则,以最优地增强学习鲁棒性或训练性能。在此基础上,我们开发了一种学习算法并提供了理论收敛分析。仿真结果验证了 fluid antenna 在提升 FL 性能方面的有效性,展示了其作为无线 AI 应用关键使能技术的潜力。

英文摘要:

Federated learning (FL) is an emerging machine learning paradigm with immense potential to support advanced services and applications in future industries. However, when deployed over wireless communication systems, FL suffers from significant communication overhead, which can be alleviated by integrating over-the-air computation (AirComp). Despite its advantages, AirComp introduces learning inaccuracies due to the inherent randomness of wireless channels, which can degrade overall learning performance. To address this issue, this paper explores the integration of fluid antenna systems (FAS) into AirComp-based FL to enhance system robustness and efficiency. Fluid antennas offer dynamic spatial diversity by adaptively selecting antenna ports, thereby mitigating channel variations and improving signal aggregation. Specifically, we propose an antenna selection rule for fluid-antenna-equipped devices that optimally enhances learning robustness or training performance. Building on this, we develop a learning algorithm and provide a theoretical convergence analysis. The simulation results validate the effectiveness of fluid antennas in improving FL performance, demonstrating their potential as a key enabler for wireless AI applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑