Special Issue "Federated Machine Learning on Digital Health"

Submission Deadline: 15 September 2021 (closed)
Guest Editors
Dr. Yu-Dong Zhang, University of Leicester, UK.
Dr. Juan Manuel Gorriz, University of Granada, Spain.
Dr. Yuankai Huo, Vanderbilt University, USA.

Summary

Federated machine learning (FML) is a new machine learning technique that trains an algorithm across multiple decentralized edge devices that hold local data samples without exchanging them. FML is a broad field that links many subjects, including distributed computing, collaborative learning, machine learning, edge computing, fog computing, etc. FML is different to traditional centralized machine learning techniques where all the local datasets are uploaded to one device.

 

Recently, FML shows promising results in solving data privacy problems in digital health, as FML can train the algorithms without exchanging the data. Its ability to train machine learning/deep learning frameworks at scale across multiple hospitals/institutions without moving the data is a critical technology to protect privacy.

 

The aim of this special section is to provide a diverse, but complementary, set of contributions to demonstrate new developments and applications of FML to solve problems in digital health. The ultimate goal is to promote research and development of FML by publishing high-quality survey and research articles in this rapidly growing digital health field.


Keywords
Federated machine learning; deep learning; artificial intelligence; cloud computing; machine learning; digital health