AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation

Author:

Varno FarshidORCID,Saghayi MarzieORCID,Rafiee Sevyeri LayaORCID,Gupta SharutORCID,Matwin StanORCID,Havaei MohammadORCID

Publisher

Springer Nature Switzerland

Reference33 articles.

1. Acar, D.A.E., Zhao, Y., Matas, R., Mattina, M., Whatmough, P., Saligrama, V.: Federated learning based on dynamic regularization. In: International Conference on Learning Representations (2020)

2. Ajalloeian, A., Stich, S.U.: On the convergence of SGD with biased gradients. arXiv preprint arXiv:2008.00051 (2020)

3. Harikandeh, R.B., Ahmed, M.O., Virani, A., Schmidt, M., Konečnỳ, J., Sallinen, S.: Stopwasting my gradients: practical svrg. Adv. Neural Inf. Process. Syst. 28 (2015)

4. Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence);J Bi,2021

5. Hsu, T.M.H., Qi, H., Brown, M.: Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019)

Cited by 9 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. TSFed: A three-stage optimization mechanism for secure and efficient federated learning in industrial IoT networks;Internet of Things;2024-10

2. A Cross-Client Coordinator in Federated Learning Framework for Conquering Heterogeneity;IEEE Transactions on Neural Networks and Learning Systems;2024

3. Accelerating Federated Learning via Sequential Training of Grouped Heterogeneous Clients;IEEE Access;2024

4. Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning;2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW);2023-10-02

5. Improving Communication Efficiency: A Dual Adaptive Federated Learning Framework;2023 38th Youth Academic Annual Conference of Chinese Association of Automation (YAC);2023-08-27

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3