arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07776cs.LGcs.CRcs.DCcs.ITmath.ITstat.ML
收藏

基于差分隐私约束的多址信道联邦学习

Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints

National Chiao Tung University (NCTU)(国立交通大学)

Amir Sonee, Stefano Rini

摘要:

在本文中,联邦学习(FL)的问题,通过客户端和参数服务器(PS)之间的数字通信通过多访问信道(MAC),也受到差分隐私(DP)的约束,进行了研究。更准确地说,我们考虑这样一种设置,其中集中式网络中的客户端被提示使用其本地数据集来训练机器学习模型。客户端和PS之间的信息交换通过MAC信道进行,并且还必须保留本地数据集的DP。因此,客户端的目标是使训练损失最小化,该训练损失受制于(i)用于在MAC上的可靠通信的速率约束和(ii)在本地数据集上的DP约束。对于这种优化方案,我们提出了一种新的共识方案,其中每个客户端执行数字分布式随机梯度下降(D-DSGD)。为了保持DP,用户还将数字人工噪声添加到局部量化的梯度。该计划的性能进行评估的收敛速度和DP水平为一个给定的MAC容量。通过量化电平和人工噪声参数的选择优化了性能。数值计算结果验证了该方案的性能。

英文摘要:

In this paper, the problem of federated learning (FL) through digital communication between clients and a parameter server (PS) over a multiple access channel (MAC), also subject to differential privacy (DP) constraints, is studied. More precisely, we consider the setting in which clients in a centralized network are prompted to train a machine learning model using their local datasets. The information exchange between the clients and the PS takes places over a MAC channel and must also preserve the DP of the local datasets. Accordingly, the objective of the clients is to minimize the training loss subject to (i) rate constraints for reliable communication over the MAC and (ii) DP constraint over the local datasets. For this optimization scenario, we proposed a novel consensus scheme in which digital distributed stochastic gradient descent (D-DSGD) is performed by each client. To preserve DP, a digital artificial noise is also added by the users to the locally quantized gradients. The performance of the scheme is evaluated in terms of the convergence rate and DP level for a given MAC capacity. The performance is optimized over the choice of the quantization levels and the artificial noise parameters. Numerical evaluations are presented to validate the performance of the proposed scheme.

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。

↑