Federated Learning Versus Classical Machine Learning: A Convergence Comparison
Federated Learning Versus Classical Machine Learning: A Convergence Comparison
复制标题
DOI：
10.22541/au.162074596.66890690/v1
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Muhammad Asad;Ahmed Moustafa;Takayuki Ito
中科院分区：
文献类型：
--
作者：
Muhammad Asad;Ahmed Moustafa;Takayuki Ito
在过去的几十年里，机器学习已经彻底改变了大规模应用的数据处理。与此同时，趋势应用程序中越来越多的隐私威胁导致了对经典数据训练模型的重新设计。特别是，经典机器学习涉及集中式数据训练，其中收集数据，整个训练过程在中央服务器上执行。尽管有显著的融合，但当与中央云服务器共享时，此培训涉及参与者数据的几个隐私威胁。为此，联邦学习在分布式数据训练中具有重要意义。特别是，联邦学习允许参与者根据本地数据协作训练本地模型，而无需向中央云服务器透露其敏感信息。在本文中，我们在两个公开可用的数据集上，即逻辑回归MNIST数据集和图像分类CIFAR-10数据集，对经典机器学习和联邦学习进行了收敛性比较。仿真结果表明，联邦学习在保持参与者匿名性的同时，在有限的通信轮次内实现了更高的收敛性。我们希望这项研究能够显示出它的好处，并帮助联邦学习得到广泛的实施。
In the past few decades, machine learning has revolutionized data processing for large scale applications. Simultaneously , increasing privacy threats in trending applications led to the redesign of classical data training models. In particular, classical machine learning involves centralized data training, where the data is gathered, and the entire training process executes at the central server. Despite significant convergence, this training involves several privacy threats on participants’ data when shared with the central cloud server. To this end, federated learning has achieved significant importance over distributed data training. In particular, the federated learning allows participants to collaboratively train the local models on local data without revealing their sensitive information to the central cloud server. In this paper, we perform a convergence comparison between classical machine learning and federated learning on two publicly available datasets, namely, logistic-regression-MNIST dataset and image-classification-CIFAR-10 dataset. The simulation results demonstrate that federated learning achieves higher convergence within limited communication rounds while maintaining participants’ anonymity. We hope that this research will show the benefits and help federated learning to be implemented widely.