Skip to main content
QUICK REVIEW

[论文解读] Resource Allocation of Federated Learning for the Metaverse with Mobile Augmented Reality

Xinyu Zhou, Chang Liu|arXiv (Cornell University)|Nov 16, 2022
Privacy-Preserving Technologies in Data被引用 4
一句话总结

本文提出了一种面向元宇宙中移动增强现实(MAR)系统联邦学习(FL)的联合资源分配框架,通过优化带宽、传输功率、CPU频率和视频分辨率,最小化能量、延迟和模型准确率的加权组合。该算法在所有指标上均优于基线方法,尤其在严格时间约束下表现更优。

ABSTRACT

The Metaverse has received much attention recently. Metaverse applications via mobile augmented reality (MAR) require rapid and accurate object detection to mix digital data with the real world. Federated learning (FL) is an intriguing distributed machine learning approach due to its privacy-preserving characteristics. Due to privacy concerns and the limited computation resources on mobile devices, we incorporate FL into MAR systems of the Metaverse to train a model cooperatively. Besides, to balance the trade-off between energy, execution latency and model accuracy, thereby accommodating different demands and application scenarios, we formulate an optimization problem to minimize a weighted combination of total energy consumption, completion time and model accuracy. Through decomposing the non-convex optimization problem into two subproblems, we devise a resource allocation algorithm to determine the bandwidth allocation, transmission power, CPU frequency and video frame resolution for each participating device. We further present the convergence analysis and computational complexity of the proposed algorithm. Numerical results show that our proposed algorithm has better performance (in terms of energy consumption, completion time and model accuracy) under different weight parameters compared to existing benchmarks.

研究动机与目标

  • 解决在元宇宙赋能的移动增强现实(MAR)应用中训练高精度、隐私保护型目标检测模型的挑战。
  • 通过将联邦学习(FL)集成到MAR系统中,克服数据可用性不足与隐私顾虑。
  • 构建一个联合优化问题,平衡联邦学习-MAR系统中的能耗、完成时间与模型准确率。
  • 设计一种资源分配算法,动态分配每台设备的带宽、传输功率、CPU频率和视频分辨率。
  • 通过调节多目标优化中的权重参数,确保算法可适应多样化应用场景。

提出的方法

  • 构建一个非凸多目标优化问题,最小化总能耗、完成时间与模型准确率的加权和。
  • 将问题分解为两个子问题:传输资源分配与计算资源分配,通过迭代方式求解。
  • 采用Dinkelbach方法处理能耗-延迟权衡中的分数规划特性。
  • 基于延迟与计算约束推导的表达式,固定每台设备的CPU频率,以确保可行性。
  • 应用序列凸逼近(SCA)处理传输功率与带宽优化中的非凸性。
  • 将视频帧分辨率作为优化变量,以减少数据传输量,同时保持模型性能。
Figure 1 : Federated learning with mobile augmented reality (FL-MAR) for the Metaverse.
Figure 1 : Federated learning with mobile augmented reality (FL-MAR) for the Metaverse.

实验结果

研究问题

  • RQ1如何在带宽、传输功率、CPU频率与视频分辨率之间联合优化FL-MAR系统的资源分配,以平衡能耗、延迟与准确率?
  • RQ2权重参数的变化对FL-MAR系统中能耗效率、训练完成时间与模型准确率之间权衡的影响是什么?
  • RQ3所提算法与仅优化传输或仅优化计算能耗的基线方案相比表现如何?
  • RQ4在何种场景下,所提算法显著优于现有方法,尤其是在严格时间约束下?
  • RQ5所提资源分配算法的收敛特性与计算复杂度如何?

主要发现

  • 在所有测试的权重参数下,所提算法的总能耗均低于仅计算(Computation-only)与仅传输(Transmission-only)方案。
  • 传输能耗占总能耗的主导地位,表明传输资源优化对节能至关重要。
  • 随着最大完成时间的缩短,所提算法与基线方案(Scheme 1)之间的性能差距增大,表明在严苛延迟约束下表现更优。
  • 在完成时间为150秒时,由于初始传输功率设置较高,所提算法呈现非单调能耗趋势,但仍优于基线。
  • 该算法收敛稳定,计算复杂度可控,适用于元宇宙MAR系统中的实时部署。
  • 联合优化视频帧分辨率显著提升了整体系统性能;若移除该变量,系统有效性将明显下降。
Figure 2 : Illustration of the 1st convolutional layer in a CNN. In this example, padding is 0 and stride is 1. $c_{0}$ is the default number of channels (e.g., in a color image, we have three channels). $c_{1}$ is the number of kernels, the same as the number of output channels. $m_{1}$ is calculat
Figure 2 : Illustration of the 1st convolutional layer in a CNN. In this example, padding is 0 and stride is 1. $c_{0}$ is the default number of channels (e.g., in a color image, we have three channels). $c_{1}$ is the number of kernels, the same as the number of output channels. $m_{1}$ is calculat

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。