Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT-Reference-Cited by-同舟云学术

Data Heterogeneity-Robust Federated Learning via Group Client Selection in Industrial IoT

Published:2022-09-15 Issue:18 Volume:9 Page:17844-17857
ISSN:2327-4662
Container-title:IEEE Internet of Things Journal
language:
Short-container-title:IEEE Internet Things J.

Author:

Li Zonghang¹^ORCID,He Yihong¹^ORCID,Yu Hongfang¹^ORCID,Kang Jiawen²^ORCID,Li Xiaoping³^ORCID,Xu Zenglin⁴^ORCID,Niyato Dusit⁵^ORCID

Affiliation:

1. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China

2. School of Automation, Guangdong University of Technology, Guangzhou, China

3. School of Mathematical Science, University of Electronic Science and Technology of China, Chengdu, China

4. School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China

5. School of Computer Science and Engineering, Nanyang Technological University, Singapore

Funder

Development Program of China

National Natural Science Foundation of China

PCL Future Greater Bay Area Network Facilities for Large-Scale Experiments and Applications

Open Research Projects of Zhejiang Lab

Key Program of Fundamental Research from Shenzhen Science and Technology Innovation Commission

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer Networks and Communications,Computer Science Applications,Hardware and Architecture,Information Systems,Signal Processing

Link

http://xplorestaging.ieee.org/ielx7/6488907/9881201/09741255.pdf?arnumber=9741255

Reference51 articles.

1. AdaGrad stepsizes: Sharp convergence over nonconvex landscapes;ward;Proc Int Conf Mach Learn,2019

2. Gradient methods for minimizing composite functions

3. Adaptive federated optimization;reddi;Proc Int Conf Learn Represent,2021

4. Measuring the effects of non-identical data distribution for federated visual classification;hsu;Proc Int Workshop Federated Learn Data Privacy Confidentiality in Conjunct NeurIPS,2019

5. Client adaptation improves federated learning with simulated non-IID clients;rieger;Proc Int Workshop Federated Learn User Privacy Data Confidentiality Conjunct,2020

Cited by 76 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. A personalized federated meta-learning method for intelligent and privacy-preserving fault diagnosis;Advanced Engineering Informatics;2024-10

2. BC4LLM: A perspective of trusted artificial intelligence when blockchain meets large language models;Neurocomputing;2024-09

3. Topology Learning for Heterogeneous Decentralized Federated Learning Over Unreliable D2D Networks;IEEE Transactions on Vehicular Technology;2024-08

4. A Survey of Trustworthy Federated Learning: Issues, Solutions, and Challenges;ACM Transactions on Intelligent Systems and Technology;2024-07-23

5. Ensuring Fairness in Federated Learning Services: Innovative Approaches to Client Selection, Scheduling, and Rewards;2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS);2024-07-23