arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.14787cs.DC
收藏

联邦学习的综述与展望

A Generalized Look at Federated Learning: Survey and Perspectives

Taki Hasan Rafi, Faiza Anan Noor, Tahmid Hussain, Dong-Kyu Chae, Zhaohui Yang

摘要:

联邦学习(FL)是指一种分布式机器学习框架,涉及从多个分散的边缘客户端学习,而无需共享本地数据集。这种分布式策略可以防止数据泄漏,并支持设备上的训练,因为它可以根据本地模型更新来更新全局模型。尽管FL提供了一些优势,包括数据隐私和可扩展性,但它也带来了挑战,例如联邦网络中数据的统计和系统异构性,通信瓶颈,隐私和安全问题。本调查包含了对以前的工作,研究和实验的系统总结,并提出了一系列应用和用例的FL的可能性列表。除此之外,实施FL的各种挑战和围绕相应的挑战有希望的方向。

英文摘要:

Federated learning (FL) refers to a distributed machine learning framework involving learning from several decentralized edge clients without sharing local dataset. This distributed strategy prevents data leakage and enables on-device training as it updates the global model based on the local model updates. Despite offering several advantages, including data privacy and scalability, FL poses challenges such as statistical and system heterogeneity of data in federated networks, communication bottlenecks, privacy and security issues. This survey contains a systematic summarization of previous work, studies, and experiments on FL and presents a list of possibilities for FL across a range of applications and use cases. Other than that, various challenges of implementing FL and promising directions revolving around the corresponding challenges are provided.

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。

↑