Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space-Reference-Cited by-同舟云学术

Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space

Published:2022 Issue: Volume:8 Page:799-814
ISSN:2373-776X
Container-title:IEEE Transactions on Signal and Information Processing over Networks
language:
Short-container-title:IEEE Trans. on Signal and Inf. Process. over Networks

Author:

Taya Akihito¹^ORCID,Nishio Takayuki²^ORCID,Morikura Masahiro³^ORCID,Yamamoto Koji³^ORCID

Affiliation:

1. College of Science and Engineering, Department of Integrated Information Technology, Aoyama Gakuin University, Sagamihara, Japan

2. School of Engineering, Tokyo Tech., Meguro City, Japan

3. Graduate School of Informatics, Kyoto University, Kyoto, Japan

Funder

JSPS KAKENHI

JST PRESTO

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer Networks and Communications,Information Systems,Signal Processing

Link

Reference48 articles.

1. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms;xiao,2017

5. Decentralised learning with random features and distributed gradient descent;richards;Proc 37th Int Conf Mach Learn,0

Cited by 6 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. Privacy Leakage from Logits Attack and its Defense in Federated Distillation;2024 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN);2024-06-24

4. Non-static TinyML for ad hoc networked devices;TinyML for Edge Intelligence in IoT and LPWAN Networks;2024