arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.08329cs.LGcs.DCstat.ML
收藏

从基于服务器到基于客户端的机器学习:一个全面的综述

From Server-Based to Client-Based Machine Learning: A Comprehensive Survey

Shanghai Jiao Tong University(上海交通大学);Alibaba(阿里巴巴)

Renjie Gu, Chaoyue Niu, Fan Wu, Guihai Chen, Chun Hu, Chengfei Lyu, Zhihua Wu

摘要:

近年来,移动设备以更强的计算能力和更大的存储空间获得了日益增长的发展。一些计算密集型的机器学习任务现在可以在移动设备上运行。为了利用移动设备上可用的资源并保护个人隐私,已经提出了基于客户端的机器学习的概念。它利用用户的本地硬件和本地数据在移动设备上解决机器学习子问题,只上传计算结果而不是原始数据,用于全局模型的优化。这样的架构不仅可以减轻服务器的计算和存储负担,还可以保护用户的敏感信息。另一个好处是带宽减少,因为各种本地数据可以参与训练过程而无需上传。在这篇文章中,我们提供了一个文献综述的逐步发展的机器学习从基于服务器到基于客户端。我们回顾了一些广泛使用的基于服务器和基于客户端的机器学习方法和应用程序。我们还广泛讨论了这一领域的挑战和未来方向。我们相信,这项调查将对基于客户端的机器学习进行清晰的概述,并为将基于客户端的机器学习应用于实践提供指导。

英文摘要:

In recent years, mobile devices have gained increasing development with stronger computation capability and larger storage space. Some of the computation-intensive machine learning tasks can now be run on mobile devices. To exploit the resources available on mobile devices and preserve personal privacy, the concept of client-based machine learning has been proposed. It leverages the users' local hardware and local data to solve machine learning sub-problems on mobile devices and only uploads computation results rather than the original data for the optimization of the global model. Such an architecture can not only relieve computation and storage burdens on servers but also protect the users' sensitive information. Another benefit is the bandwidth reduction because various kinds of local data can be involved in the training process without being uploaded. In this article, we provide a literature review on the progressive development of machine learning from server based to client based. We revisit a number of widely used server-based and client-based machine learning methods and applications. We also extensively discuss the challenges and future directions in this area. We believe that this survey will give a clear overview of client-based machine learning and provide guidelines on applying client-based machine learning to practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑