With more regulations tackling users' privacy-sensitive data protection in recent years, access to such data has become increasingly restricted and controversial. To exploit the wealth of data generated and located at distributed entities such as mobile phones, a revolutionary decentralized machine learning setting, known as Federated Learning, enables multiple clients located at different geographical locations to collaboratively learn a machine learning model while keeping all their data on-device. However, the scale and decentralization of federated learning present new challenges. Communication between the clients and the server is considered a main bottleneck in the convergence time of federated learning. In this paper, we propose and study Adaptive Federated Dropout (AFD), a novel technique to reduce the communication costs associated with federated learning. It optimizes both server-client communications and computation costs by allowing clients to train locally on a selected subset of the global model. We empirically show that this strategy, combined with existing compression methods, collectively provides up to 57x reduction in convergence time. It also outperforms the state-of-the-art solutions for communication efficiency. Furthermore, it improves model generalization by up to 1.7%.
翻译:近年来,随着处理用户隐私敏感数据保护的条例的增多,此类数据的获取日益受到限制和争议。为了利用移动电话等分布式实体产生和储存的大量数据,一个革命性的分散式机器学习环境,即Federed Learning,使位于不同地理位置的多个客户能够合作学习机器学习模式,同时将其所有数据保存在设备上。然而,联邦学习的规模和分散化带来了新的挑战。客户与服务器之间的沟通被视为联合学习时间融合过程中的一个主要瓶颈。我们在本文件中提出并研究适应性联邦辍学(AFD),这是一种减少与联合学习有关的通信费用的新技术。它优化服务器客户通信和计算成本,允许客户在特定的全球模型中就特定组别进行本地培训。我们从经验上表明,这一战略,加上现有的压缩方法,共同减少了57x的整合时间。它也超越了通信效率方面最先进的解决方案。此外,它提高了模型的普及程度,达到1.7%。