当前位置: X-MOL 学术arXiv.eess.SP › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
UAV-Assisted Hierarchical Aggregation for Over-the-Air Federated Learning
arXiv - EE - Signal Processing Pub Date : 2022-09-23 , DOI: arxiv-2209.11624
Xiangyu Zhong, Xiaojun Yuan, Huiyuan Yang, Chenxi Zhong

With huge amounts of data explosively increasing in the mobile edge, over-the-air federated learning (OA-FL) emerges as a promising technique to reduce communication costs and privacy leak risks. However, when devices in a relatively large area cooperatively train a machine learning model, the attendant straggler issues will significantly reduce the learning performance. In this paper, we propose an unmanned aerial vehicle (UAV) assisted OA-FL system, where the UAV acts as a parameter server (PS) to aggregate the local gradients hierarchically for global model updating. Under this UAV-assisted hierarchical aggregation scheme, we carry out a gradient-correlation-aware FL performance analysis. We then formulate a mean squared error (MSE) minimization problem to tune the UAV trajectory and the global aggregation coefficients based on the analysis results. An algorithm based on alternating optimization (AO) and successive convex approximation (SCA) is developed to solve the formulated problem. Simulation results demonstrate the great potential of our UAV-assisted hierarchical aggregation scheme.

中文翻译:

用于空中联合学习的无人机辅助分层聚合

随着移动边缘的大量数据爆炸式增长,空中联合学习(OA-FL)成为一种很有前途的技术,可以降低通信成本和隐私泄露风险。然而,当较大区域内的设备协同训练机器学习模型时,随之而来的落后问题会显着降低学习性能。在本文中,我们提出了一种无人机 (UAV) 辅助 OA-FL 系统,其中无人机充当参数服务器 (PS) 以分层聚合局部梯度以进行全局模型更新。在这种无人机辅助的分层聚合方案下,我们进行了梯度相关感知 FL 性能分析。然后,我们制定了一个均方误差 (MSE) 最小化问题,以根据分析结果调整无人机轨迹和全局聚合系数。开发了一种基于交替优化(AO)和逐次凸逼近(SCA)的算法来解决公式化问题。仿真结果证明了我们的无人机辅助分层聚合方案的巨大潜力。
更新日期:2022-09-26
down
wechat
bug