【Author】
Liu, Yinghui; Qu, Youyang; Xu, Chenhao; Hao, Zhicheng; Gu, Bruce
【Abstract】The fast proliferation of edge computing devices brings an increasing growth of data, which directly promotes machine learning (ML) technology development. However, privacy issues during data collection for ML tasks raise extensive concerns. To solve this issue, synchronous federated learning (FL) is proposed, which enables the central servers and end devices to maintain the same ML models by only exchanging model parameters. However, the diversity of computing power and data sizes leads to a significant difference in local training data consumption, and thereby causes the inefficiency of FL. Besides, the centralized processing of FL is vulnerable to single-point failure and poisoning attacks. Motivated by this, we propose an innovative method, federated learning with asynchronous convergence (FedAC) considering a staleness coefficient, while using a blockchain network instead of the classic central server to aggregate the global model. It avoids real-world issues such as interruption by abnormal local device training failure, dedicated attacks, etc. By comparing with the baseline models, we implement the proposed method on a real-world dataset, MNIST, and achieve accuracy rates of 98.96% and 95.84% in both horizontal and vertical FL modes, respectively. Extensive evaluation results show that FedAC outperforms most existing models.
【Keywords】federated learning; blockchain; edge computing; asynchronous convergence
【摘要】边缘计算设备的快速普及带来了数据的不断增长，这直接推动了机器学习（ML）技术的发展。然而，机器学习任务的数据收集过程中的隐私问题引起了广泛的关注。为了解决这个问题，提出了同步联邦学习（FL），它使中央服务器和终端设备仅通过交换模型参数来维护相同的机器学习模型。然而，计算能力和数据大小的多样性导致本地训练数据消耗存在显着差异，从而导致 FL 效率低下。此外，FL的集中处理容易受到单点故障和中毒攻击。受此启发，我们提出了一种创新的方法，即考虑过时系数的异步收敛联邦学习（FedAC），同时使用区块链网络而不是经典的中央服务器来聚合全局模型。它避免了现实世界中的问题，例如异常本地设备训练失败、专用攻击等造成的中断。通过与基线模型比较，我们在现实世界的数据集 MNIST 上实现了所提出的方法，并达到了 98.96% 的准确率和在水平和垂直 FL 模式下分别为 95.84%。广泛的评估结果表明，FedAC 优于大多数现有模型。
评论