A Triple-Step Asynchronous Federated Learning Mechanism for Client Activation, Interaction Optimization, and Aggregation Enhancement-Reference-Cited by-同舟云学术

A Triple-Step Asynchronous Federated Learning Mechanism for Client Activation, Interaction Optimization, and Aggregation Enhancement

Published:2022-12-01 Issue:23 Volume:9 Page:24199-24211
ISSN:2327-4662
Container-title:IEEE Internet of Things Journal
language:
Short-container-title:IEEE Internet Things J.

Author:

You Linlin¹,Liu Sheng¹^ORCID,Chang Yi²^ORCID,Yuen Chau³^ORCID

Affiliation:

1. School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China

2. School of Artificial Intelligence, Jilin University, Changchun, China

3. Engineering Product Development, Singapore University of Technology and Design, Tampines, Singapore

Funder

National Natural Science Foundation of China

Singapore Ministry of National Development and the National Research Foundation, Prime Minister’s Office through the Cities of Tomorrow (CoT) Research Programme

Collaborative Innovation Center for Transportation of Guangzhou

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/ielx7/6488907/9955314/09815310.pdf?arnumber=9815310

Reference36 articles.

1. A mutual information based federated learning framework for edge computing networks

2. Efficient decentralized deep learning by dynamic model averaging;kamp;Proc Eur Conf Mach Learn Knowl Discovery Databases,2018

3. cpSGD: Communication-efficient and differentially-private distributed SGD;agarwal;Proc 32nd Int Conf Neural Inf Process Syst,2018

4. Jointly Optimizing Client Selection and Resource Management in Wireless Federated Learning for Internet of Things

5. How transferable are features in deep neural networks?;yosinski;Proc 27th Int Conf Neural Inf Process Syst,2014

Cited by 35 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. Self-adaptive asynchronous federated optimizer with adversarial sharpness-aware minimization;Future Generation Computer Systems;2024-12

2. AFM3D: An Asynchronous Federated Meta-Learning Framework for Driver Distraction Detection;IEEE Transactions on Intelligent Transportation Systems;2024-08

3. FMGCN: Federated Meta Learning-Augmented Graph Convolutional Network for EV Charging Demand Forecasting;IEEE Internet of Things Journal;2024-07-15

4. Towards Efficient Asynchronous Federated Learning in Heterogeneous Edge Environments;IEEE INFOCOM 2024 - IEEE Conference on Computer Communications;2024-05-20

5. FedBF16-Dynamic: Communication-Efficient Federated Learning with Adaptive Transmission;IEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS);2024-05-20