FedMDS: An Efficient Model Discrepancy-Aware Semi-Asynchronous Clustered Federated Learning Framework-Reference-Cited by-同舟云学术

FedMDS: An Efficient Model Discrepancy-Aware Semi-Asynchronous Clustered Federated Learning Framework

Author:

Zhang Yu¹^ORCID,Liu Duo¹^ORCID,Duan Moming¹^ORCID,Li Li¹,Chen Xianzhang¹^ORCID,Ren Ao¹,Tan Yujuan¹,Wang Chengliang¹

Affiliation:

1. College of Computer Science, Chongqing University, Chongqing, China

Funder

National Natural Science Foundation of China

Chongqing Postdoctoral Science Foundation

Funds for Chongqing Distinguished Young Scholars

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Signal Processing

Link

Reference41 articles.

1. Achieving linear speedup with partial worker participation in non-IID federated learning;yang,2021

2. On the convergence of FedAvg on non-IID data;li,2019

4. Asynchronous federated optimization;cong xie,2019

Cited by 18 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

2. Staleness aware semi-asynchronous federated learning;Journal of Parallel and Distributed Computing;2024-11

5. CASA: Clustered Federated Learning with Asynchronous Clients;Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining;2024-08-24