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 2302.12735cs.GTcs.LG
收藏

无验证联邦学习中客户端噪声添加的调节

Regulating Clients' Noise Adding in Federated Learning without Verification

Singapore University of Technology and Design(新加坡科技设计大学)

Shu Hong, Lingjie Duan

摘要:

在联邦学习(FL)中,客户端协同训练一个全局模型,但不透露它们的原始数据,只透露梯度或参数,而本地信息仍然可以从传输到参数服务器的本地输出中透露。有了这样的隐私问题,客户端可能会过度添加人工噪声到他的本地更新,以损害全局模型的训练,我们证明了自私的噪声添加导致无政府状态(PoA)的无限无政府代价。本文提出了一种新的定价机制,以调节隐私敏感的客户端,而无需验证他们的参数更新,不像现有的隐私机制,假设服务器的全部知识增加的噪音。在不知道基础事实的情况下,我们的机制根据客户端的更新参数和所有客户端的平均参数之间的差异,达到社会最优,以最好地平衡全局训练误差和隐私损失。我们还通过改进服务器上的聚合规则来提高FL收敛范围,以考虑不同客户端的噪声方差。此外,我们扩展了我们的定价方案,以适应客户隐私敏感性的不完整信息,确保他们真实的类型报告和系统的事前预算平衡。仿真结果表明,我们的定价方案大大提高了系统的性能,特别是当客户端有不同的隐私敏感性。

英文摘要:

In federated learning (FL), clients cooperatively train a global model without revealing their raw data but gradients or parameters, while the local information can still be disclosed from local outputs transmitted to the parameter server. With such privacy concerns, a client may overly add artificial noise to his local updates to compromise the global model training, and we prove the selfish noise adding leads to an infinite price of anarchy (PoA). This paper proposes a novel pricing mechanism to regulate privacy-sensitive clients without verifying their parameter updates, unlike existing privacy mechanisms that assume the server's full knowledge of added noise. Without knowing the ground truth, our mechanism reaches the social optimum to best balance the global training error and privacy loss, according to the difference between a client's updated parameter and all clients' average parameter. We also improve the FL convergence bound by refining the aggregation rule at the server to account for different clients' noise variances. Moreover, we extend our pricing scheme to fit incomplete information of clients' privacy sensitivities, ensuring their truthful type reporting and the system's ex-ante budget balance. Simulations show that our pricing scheme greatly improves the system performance especially when clients have diverse privacy sensitivities.

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。

↑