Optimizing Federated Learning on Non-IID Data with Reinforcement Learning文章链接：https://ieeexplore.ieee.org/document/9155494/作者：Hao Wang，Zakhary Kaplan，Di Niu，Baochun Li发表：IEEE INFOCOM 2020 - IEEE Confe
Threats to Federated Learning: A Survey文章链接：https://arxiv.org/abs/2003.02133作者：Lingjuan Lyu, Han Yu, Qiang Yang发表：arXiv截止当前（2020.12.20）被引次数：24Zotero链接: 从我的文库打开标签1标签2标签3标签4 [toc]Summary本文侧重危及FL的威胁的最
Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges文章链接：https://arxiv.org/abs/1908.06847v4作者：Solmaz Niknam, Harpreet S. Dhillon, Jeffery H. Reed发表：arXiv截止当前（2020.1
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection文章地址：https://arxiv.org/abs/1907.09693作者：Qinbin Li, Zeyi Wen, Zhaomin Wu, Sixu Hu, Naibo Wang, Bingsheng
A Systematic Literature Review on Federated Machine Learning: From A Software Engineering Perspective文献链接：https://arxiv.org/pdf/2007.11354.pdf作者：Sin Kit Lo, Qinghua Lu, Chen Wang, Hye-Young Paik, Limi
Client Selection for Federated Learning with Heterogeneous Resources in Mobile EdgeZotero链接: 从我的文库打开标签1标签2标签3标签4Federated LearningClient SelectionFedCSMEC回顾本文重点内容见Conclusion。论文阅读笔记仅供参考交流~[TOC]Abstract
写在前面 参考文献《Federated Learning: Challenges, methods, and future, 2020》，较为详细的介绍当前FL的挑战和解决方法以及未来可能的研究方向或切入点。Federated Learning: Challenges, methods, and future摘要 联邦学习在保持数据本地化的同时涉及在远程设备或孤立的数据中心（例如
写在前面 参考文献《Advances and Open Problems in Federated Learning, 2019》，58位作者的105页文章。笔者当前花了一些时间来阅读这篇论文，由于能力有限，只做一些感兴趣点的记录和分析。另引用内容见文末参考文献，如侵权请联系笔者。欢迎讨论~Advances and Open Problems in Federated Learning,
