IEEE Consumer Electronics Magazine - November/December 2021 - 106

Product and Book Reviews
Federated Learning
Niranjan K. Ray
KIIT University
Deepak Puthal
Newcastle University
Dhruva Ghai
Oriental University
& NOW WE ARE in an era of technology transformation
in our everyday life, where data play a key
role in the decision making and bringing the
action into reality. These data are collected from
many distributed sources. Another important
concept in this process is machine learning (ML)
and data analytics. Federated learning (FL) is the
term coined by Google. It facilitated the distributed
learning process and shared the results to
the outcomes to the central entity instead of conducting
the complete learning process at the centre.
In the traditional machine learning approach,
data are brought to the model. Whereas FL brings
ML techniques to the data used at end devices. In
a nutshell, FL, which is also known as distributed
learning deals with both centralized and distributed
devices. The central entity(server) selects
the statistical model which is to be trained. Then,
it sends the trained model to multiple decentralized
devices or servers. These distributed nodes
train the model locally with their own data.
Finally, the central entity pools the results from
the distributed nodes and prepares a common
model without accessing the data from the other
nodes.1,2
Digital Object Identifier 10.1109/MCE.2021.3094778
Date ofpublication 8 July 2021; date ofcurrent version
6 October 2021.
Federated learning has some advantages over
ML and Deep Learning. It maintains the privacy by
not sharing all the data with the central entity, and
the data are processed in a distributed manner,
which is efficient in latency and resource utilization.
Concurrently, many research issues have
being popup with Federated Learning deployment,
such as i) how to maintain data and device
security during the learning process? and ii) how
to detect and mitigate the flaws of the learning
process? etc.2
Federated Learning by Qiang Yang, Yang Liu,
Yong Cheng, Yan Kang, Tianjian Chen and Han
Yu is all about collaborative machine learning
technique.1 The book focuses on the application
of different ML techniques in artificial intelligence
(AI). It has eleven chapters, which
includes an introduction and Summary. There
are 32 pages of references, and most of the references
are from 2014 to recent, and it includes
full insight into state-of-art FL. New research
directions on FL are discussed in different chapters.
By reviewing this book, we open up the different
concept, applications, and architecture of
FL. In the present Internet of Things (IoT) era,
data are huge and are stored at end devices. In
many applications, data from different devices
need to be gathered. However, due to privacy
and security concerns, it is infeasible to merge
106
2162-2248 ß 2021 IEEE
Published by the IEEE Consumer Technology Society
IEEE Consumer Electronics Magazine
IEEE Consumer Electronics Magazine - November/December 2021

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - November/December 2021
