RETRACTED: Personalized federated learning framework for network traffic anomaly detection

This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the Authors. The outcomes of the experiments were obtained with a single client, as the Authors set the number of cl...

Full description

Saved in:
Bibliographic Details
Published in:Computer networks (Amsterdam, Netherlands : 1999) Netherlands : 1999), 2022-05, Vol.209, p.108906, Article 108906
Main Authors: Pei, Jiaming, Zhong, Kaiyang, Jan, Mian Ahmad, Li, Jinhai
Format: Article
Language:English
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article has been retracted: please see Elsevier Policy on Article Withdrawal (https://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the Authors. The outcomes of the experiments were obtained with a single client, as the Authors set the number of clients to one. This was in contrast to the federated learning system, which was designed to work with multiple clients. When the Authors altered the experimental settings to accommodate more clients, the method failed to converge. Although the dataset was divided into ten clients, the Authors only trained a single model and did not include significant aggregation. As a result, the findings of the article cannot be considered convincing or reproducible.
ISSN:1389-1286
1872-7069
DOI:10.1016/j.comnet.2022.108906