论文标题
D2P-FED：通过有效沟通的差异私人联合学习
D2P-Fed: Differentially Private Federated Learning With Efficient Communication
论文作者
论文摘要
在本文中，我们提出了基于离散的高斯差异化联合学习（D2P-FED），这是一个统一的计划，旨在实现差异隐私（DP）和联合学习（FL）的沟通效率。特别是，与唯一的照顾这两个方面的工作相比，D2P喂养提供了更强的隐私保证，更好的合成性和较小的沟通成本。关键的想法是将离散的高斯噪声应用于私人数据传输。我们提供了D2P喂养的隐私保证，沟通成本和收敛率的完整分析。我们评估了d2p喂养的infimnist和cifar10。结果表明，D2P喂养的表现优于模型准确性，同时节省了三分之一的通信成本，将其胜过4.7％至13.0％。
In this paper, we propose the discrete Gaussian based differentially private federated learning (D2P-Fed), a unified scheme to achieve both differential privacy (DP) and communication efficiency in federated learning (FL). In particular, compared with the only prior work taking care of both aspects, D2P-Fed provides stronger privacy guarantee, better composability and smaller communication cost. The key idea is to apply the discrete Gaussian noise to the private data transmission. We provide complete analysis of the privacy guarantee, communication cost and convergence rate of D2P-Fed. We evaluated D2P-Fed on INFIMNIST and CIFAR10. The results show that D2P-Fed outperforms the-state-of-the-art by 4.7% to 13.0% in terms of model accuracy while saving one third of the communication cost.
