FedSULP: A communication-efficient federated learning framework with selective updating and loss penalization-Reference-Cited by-同舟云学术

FedSULP: A communication-efficient federated learning framework with selective updating and loss penalization

Published:2023-12 Issue: Volume:651 Page:119725
ISSN:0020-0255
Container-title:Information Sciences
language:en
Short-container-title:Information Sciences

Author:

Nanor Ebenezer,Cobbinah Mawuli B.,Qinli Yang^ORCID,Junming Shao^ORCID,Kobiah Christiana^ORCID

Funder

Sichuan Province Science and Technology Support Program

National Natural Science Foundation of China

Fok Ying Tong Education Foundation

Fundamental Research Funds for the Central Universities

Publisher

Elsevier BV

Subject

Artificial Intelligence,Information Systems and Management,Computer Science Applications,Theoretical Computer Science,Control and Systems Engineering,Software

Reference49 articles.

1. Qsgd: communication-efficient sgd via gradient quantization and encoding;Alistarh;Adv. Neural Inf. Process. Syst.,2017

2. signsgd: compressed optimisation for non-convex problems;Bernstein,2018

3. Federated learning and privacy: building privacy-preserving systems for machine learning and data science on decentralized data;Bonawitz;Queue,2021

Cited by 5 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. Federated Dual Averaging Learning Algorithm with Delayed Gradients for Composite Optimization;Information Sciences;2024-08

2. Two-stage sampling with predicted distribution changes in federated semi-supervised learning;Knowledge-Based Systems;2024-07

3. PersistVerify: Federated model ownership verification with spatial attention and boundary sampling;Knowledge-Based Systems;2024-06

4. Federated semi-supervised learning with tolerant guidance and powerful classifier in edge scenarios;Information Sciences;2024-03

5. Sparse Personalized Federated Class-Incremental Learning;2023