With the growth of machine learning techniques, privacy of data of users has become a major concern. Most of the machine learning algorithms rely heavily on large amount of data which may be collected from various sources. Collecting these data yet maintaining privacy policies has become one of the most challenging tasks for the researchers. To combat this issue, researchers have introduced federated learning, where a prediction model is learnt by ensuring the privacy of data of clients data. However, the prevalent federated learning algorithms possess an accuracy and efficiency trade-off, especially for non-IID data. In this research, we propose a centralized, neural network-based federated learning system. The centralized algorithm incorporates micro-level parallel processing inspired by the traditional mini-batch algorithm where the client devices and the server handle the forward and backward propagation respectively. We also devise a semi-centralized version of our proposed algorithm. This algorithm takes advantage of edge computing for minimizing the load from the central server, where clients handle both the forward and backward propagation while sacrificing the overall train time to some extent. We evaluate our proposed systems on five well-known benchmark datasets and achieve satisfactory performance in a reasonable time across various data distribution settings as compared to some existing benchmark algorithms.

翻译：随着机器学习技术的发展，用户数据的隐私保护已成为一个核心问题。大多数机器学习算法高度依赖可能来自不同来源的海量数据。如何在收集这些数据的同时维护隐私策略，已成为研究人员面临的最具挑战性的任务之一。为解决此问题，研究者提出了联邦学习，通过确保客户数据的隐私来训练预测模型。然而，现有的联邦学习算法在准确性-效率之间存在权衡，尤其是在处理非独立同分布（non-IID）数据时。在本研究中，我们提出了一种基于神经网络的集中式联邦学习系统。该集中式算法借鉴传统小批量算法中的微观级并行处理机制，由客户端设备与服务器分别处理前向传播和反向传播。我们进一步提出了该算法的半集中式版本。此版本利用边缘计算减轻中央服务器的负载，由客户端负责前向与反向传播，但在一定程度上牺牲了整体训练时间。我们在五个知名基准数据集上对所提系统进行了评估，实验结果表明，与现有基准算法相比，本系统能在合理时间内，针对多种数据分布设置取得令人满意的性能。