Federated Learning: Opportunities and Challenges

by   Priyanka Mary Mammen, et al.

Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.


page 1

page 2

page 3

page 4


On Safeguarding Privacy and Security in the Framework of Federated Learning

Motivated by the advancing computational capacity of wireless end-user e...

Industrial Federated Learning – Requirements and System Design

Federated Learning (FL) is a very promising approach for improving decen...

Private Federated Learning with Domain Adaptation

Federated Learning (FL) is a distributed machine learning (ML) paradigm ...

Federated Learning over Next-Generation Ethernet Passive Optical Networks

Federated Learning (FL) is a distributed machine learning (ML) type of p...

OpenFL: An open-source framework for Federated Learning

Federated learning (FL) is a computational paradigm that enables organiz...

Federated Learning for IoUT: Concepts, Applications, Challenges and Opportunities

Internet of Underwater Things (IoUT) have gained rapid momentum over the...

Towards Node Liability in Federated Learning: Computational Cost and Network Overhead

Many machine learning (ML) techniques suffer from the drawback that thei...