arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.05342eess.SP
收藏

面向用户中心的无源联邦学习的延迟与精度联合优化

Joint Optimization of Latency and Accuracy for Split Federated Learning in User-Centric Cell-Free MIMO Networks

National Mobile Communication Research Laboratory, Southeast University(东南大学国家移动通信重点实验室);Purple Mountain Laboratories(紫金山实验室);Lenovo Group, Lenovo Research(联想集团联想研究院)

Zitong Wang, Cheng Zhang, Wen Wang, Shuigen Yang, Haiming Wang, Yongming Huang

AI总结:

本文提出一种面向用户中心的无源联邦学习框架,通过联合优化延迟与精度比,提升模型训练效率。

摘要:

本文提出了一种面向用户中心的无源多输入多输出(CF-MIMO)网络的用户中心分裂联邦学习(UCSFL)框架,以支持分裂联邦学习(SFL)。在所提出的UCSFL框架中,用户在本地部署分裂子模型,而完整模型则在接入点(AP)侧的分布式处理单元(DPUs)中维护和更新,随后通过DPUs和中央处理单元(CPU)之间的两级聚合过程。在标准机器学习(ML)假设下,我们为UCSFL提供了理论收敛分析,揭示了AP集群大小是影响模型训练准确性的关键因素。受此结果启发,我们引入了一个新的性能指标,称为延迟-精度比,定义为用户每次迭代训练延迟与其AP集群加权大小的比值。基于此指标,我们提出了一个联合优化问题,以最小化最大延迟-精度比,通过联合优化上行功率控制、下行波束成形、模型分裂和AP集群。所得到的问题被分解为两个子问题,分别在不同的时间尺度上运行,为此开发了专门的算法来处理短期和长期优化。仿真结果验证了所提出算法的收敛性,并展示了UCSFL在VGG16模型的延迟-精度比方面比基线方案更有效。此外,所提出的框架能够根据变化的通信和计算资源自适应调整分裂和集群策略。基于MNIST的手写数字分类示例进一步表明,UCSFL显著加速了VGG16模型的收敛。

英文摘要:

This paper proposes a user-centric split federated learning (UCSFL) framework for user-centric cell-free multiple-input multiple-output (CF-MIMO) networks to support split federated learning (SFL). In the proposed UCSFL framework, users deploy split sub-models locally, while complete models are maintained and updated at access point (AP)-side distributed processing units (DPUs), followed by a two-level aggregation procedure across DPUs and the central processing unit (CPU). Under standard machine learning (ML) assumptions, we provide a theoretical convergence analysis for UCSFL, which reveals that the AP-cluster size is a key factor influencing model training accuracy. Motivated by this result, we introduce a new performance metric, termed the latency-to-accuracy ratio, defined as the ratio of a user's per-iteration training latency to the weighted size of its AP cluster. Based on this metric, we formulate a joint optimization problem to minimize the maximum latency-to-accuracy ratio by jointly optimizing uplink power control, downlink beamforming, model splitting, and AP clustering. The resulting problem is decomposed into two sub-problems operating on different time scales, for which dedicated algorithms are developed to handle the short-term and long-term optimizations, respectively. Simulation results verify the convergence of the proposed algorithms and demonstrate that UCSFL effectively reduces the latency-to-accuracy ratio of the VGG16 model compared with baseline schemes. Moreover, the proposed framework adaptively adjusts splitting and clustering strategies in response to varying communication and computation resources. An MNIST-based handwritten digit classification example further shows that UCSFL significantly accelerates the convergence of the VGG16 model.

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。

↑