Differentially Private Federated Learning on Non-iid Data: Convergence Analysis and Adaptive Optimization-Reference-Cited by-同舟云学术

Differentially Private Federated Learning on Non-iid Data: Convergence Analysis and Adaptive Optimization

Published:2024-09 Issue:9 Volume:36 Page:4567-4581
ISSN:1041-4347
Container-title:IEEE Transactions on Knowledge and Data Engineering
language:
Short-container-title:IEEE Trans. Knowl. Data Eng.

Author:

Chen Lin¹^ORCID,Ding Xiaofeng¹^ORCID,Bao Zhifeng²^ORCID,Zhou Pan³^ORCID,Jin Hai¹^ORCID

Affiliation:

1. National Engineering Research Center for Big Data Technology and System Lab, Services Computing Technology and System Lab, Cluster and Grid Computing Lab, Hubei Engineering Research Center on Big Data Security, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China

2. School of Computing Technolgies, RMIT University, Melbourne, VIC, Australia

3. Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China

Funder

National Natural Science Foundation of China

CCF-Huawei Populus euphratica Innovation Research Funding

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx7/69/10629652/10475543.pdf?arnumber=10475543

Reference56 articles.

1. Communication-efficient learning of deep networks from decentralized data;McMahan

2. Advances and Open Problems in Federated Learning

3. Jupiter: a modern federated learning platform for regional medical care

4. Clustered sampling: Low-variance and improved representativity for clients selection in federated learning;Fraboni

5. Tackling the objective inconsistency problem in heterogeneous federated optimization;Wang

Cited by 1 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 Multifaceted Survey on Federated Learning: Fundamentals, Paradigm Shifts, Practical Issues, Recent Developments, Partnerships, Trade-Offs, Trustworthiness, and Ways Forward;IEEE Access;2024