arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.07972cs.NIcs.LGeess.SP
收藏

基于无线网络的联邦学习:一种带限协调下降方法

Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach

Arizona State University(亚利桑那州立大学);Harvard University(哈佛大学)

Junshan Zhang, Na Li, Mehmet Dedeoglu

摘要:

我们考虑在网络边缘进行联邦学习的多对一无线架构,其中多个边缘设备使用本地数据协作训练模型。无线连接的不可靠性质以及边缘设备处的计算资源的约束,决定了边缘设备处的本地更新应该被精心制作和压缩以匹配可用的无线通信资源,并且应该与接收器协同工作。因此,出于动机,我们提出了基于SGD的带限坐标下降算法,这样的设置。具体地,对于采用空中计算的无线边缘,接收器在每次迭代中选择边缘设备上的梯度更新的k坐标的公共子集,然后在k个子载波上同时发送,每个子载波经历时变信道条件。我们的特点的影响,通信错误和压缩,在所产生的梯度偏差和均方误差,所提出的算法的收敛性。然后,我们研究了学习驱动的通信错误最小化通过联合优化的功率分配和学习率。我们的研究结果表明,在不同的子载波的最佳功率分配应考虑到梯度值和信道条件,从而推广广泛使用的注水政策。我们还开发了次优分布式解决方案服从实施。

英文摘要:

We consider a many-to-one wireless architecture for federated learning at the network edge, where multiple edge devices collaboratively train a model using local data. The unreliable nature of wireless connectivity, together with constraints in computing resources at edge devices, dictates that the local updates at edge devices should be carefully crafted and compressed to match the wireless communication resources available and should work in concert with the receiver. Thus motivated, we propose SGD-based bandlimited coordinate descent algorithms for such settings. Specifically, for the wireless edge employing over-the-air computing, a common subset of k-coordinates of the gradient updates across edge devices are selected by the receiver in each iteration, and then transmitted simultaneously over k sub-carriers, each experiencing time-varying channel conditions. We characterize the impact of communication error and compression, in terms of the resulting gradient bias and mean squared error, on the convergence of the proposed algorithms. We then study learning-driven communication error minimization via joint optimization of power allocation and learning rates. Our findings reveal that optimal power allocation across different sub-carriers should take into account both the gradient values and channel conditions, thus generalizing the widely used water-filling policy. We also develop sub-optimal distributed solutions amenable to implementation.

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。

↑