Federated Learning: Opportunities and Challenges
It addresses privacy issues for users in sensitive domains by enabling collaborative learning without data sharing, but it is an incremental discussion of existing concepts rather than presenting new research.
This report discusses Federated Learning (FL), a technique introduced by Google in 2016 that enables multiple devices to collaboratively learn a machine learning model without sharing private data, addressing privacy concerns in domains like healthcare and finance, but it also highlights vulnerabilities to attacks similar to other ML models.
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.