Federated Learning: Challenges, Methods, and Future Directions

Li Tian; Sahu Anit Kumar; Talwalkar Ameet; Smith Virginia

首页> 外文期刊>IEEE Signal Processing Magazine >Federated Learning: Challenges, Methods, and Future Directions

【24h】

Federated Learning: Challenges, Methods, and Future Directions

机译：联合学习：挑战，方法和未来方向

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.

机译：联合学习涉及培训统计模型，以远程设备或孤岛数据中心，例如移动电话或医院，同时保持数据本地化。在异构和潜在的大规模网络中培训介绍了需要基本偏离大规模机器学习，分布式优化和隐私保留数据分析的基本偏离的挑战。在本文中，我们讨论了联邦学习的独特特征和挑战，提供了目前方法的广泛概述，并概述了与各种研究社区相关的未来工作的几个方向。

著录项

来源
《IEEE Signal Processing Magazine》 |2020年第3期|50-60|共11页
作者
Li Tian; Sahu Anit Kumar; Talwalkar Ameet; Smith Virginia;
展开▼
作者单位

Carnegie Mellon Univ Comp Sci Dept Pittsburgh PA 15213 USA;

Bosch Ctr Artificial Intelligence Pittsburgh PA USA;

Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA|Determined AI Pittsburgh PA USA;

Carnegie Mellon Univ Machine Learning Dept Pittsburgh PA 15213 USA|Stanford Univ Stanford CA 94305 USA|Carnegie Mellon Univ Elect & Comp Engn Dept Pittsburgh PA 15213 USA;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. Federated learning for 6G communications: Challenges, methods, and future directions [J] . Liu Yi, Yuan Xingliang, Xiong Zehui, Communications, China . 2020,第9期

机译：联合学习6G通信：挑战，方法和未来方向
2. Integration of blockchain and federated learning for Internet of Things: Recent advances and future challenges [J] . Mansoor Ali, Hadis Karimipour, Muhammad Tariq Computers & Security . 2021,第Sepa期

机译：区块链和联邦学习的整合：最近的进展和未来的挑战
3. Profit-based unit commitment problem: A review of models, methods, challenges, and future directions [J] . Abdi Hamdi Renewable & Sustainable Energy Reviews . 2021,第Mara期

机译：基于利润的单位承诺问题：审查模型，方法，挑战和未来方向
4. Heralding the Future of Federated Learning Framework: Architecture, Tools and Future Directions [C] . Saneev Kumar Das, Sujit Bebortta International Conference on Cloud Computing, Data Science and Engineering . 2021

机译：覆盖联邦学习框架的未来：建筑，工具和未来方向
5. mHealth Applications: Problems, Challenges, and Future Directions [D] . Sucklal, Sirina. 2017

机译：mHealth应用程序：问题，挑战和未来方向
6. Common methods of measuring ‘informed choice’ in screening participation: Challenges and future directions [O] . Alex Ghanouni, Cristina Renzi, Susanne F Meisel, 2016

机译：衡量参与筛选时明智选择的常见方法：挑战和未来方向
7. Federated Learning: Challenges, Methods, and Future Directions [O] . Tian Li, Anit Kumar Sahu, Ameet Talwalkar, 2020

机译：联合学习：挑战，方法和未来方向
8. Approximation Methods for Inference and Learning in Belief Networks: Progress and Future Directions [R] . Pazzan, M. J. , Dechter, R. 1997

机译：信念网络中推理和学习的近似方法：进展和未来方向

Federated Learning: Challenges, Methods, and Future Directions

摘要

著录项

相似文献

相关主题

期刊订阅