Federated Learning in perspective

Federated learning (pioneered by Google) is a new class of machine learning models trained on distributed data sets, and equally important, a key privacy-preserving data technology. The contribution of this article by Philip Treleaven, Malgorzata Smietanka, and RegulAItion's Head of R&D, Hirsh Pithadia is to place Federated Learning in perspective to other data science technologies.

Federated learning (pioneered by Google) is a new class of machine learning models trained on distributed datasets, and equally important a key privacy-preserving data technology.

With huge amounts of data for analysis, organisations are faced with three major challenges: a) data comprises distributed and isolated data sets; b) analytics requires models to be trained across these independent data sets; and c) data sovereignty/privacy legislation is making collecting, sharing and
analysing data increasingly difficult.

This paper reviews federated learning both in terms of a) a federated data infrastructure for privacy-preserving data access; and b) federated machine learning applied to distributed data sets.

Given the pivotal role of federated learning, the contribution of this paper is to place it in perspective to the other data science technologies. It includes discussions of the privacy challenges facing data analytics, relationship to the major data infrastructure technologies, and the emerging machine learning algorithms impacting federated learning.

A PDF of the article on the RegulAItion site is available here: Federated Learning

The article is also available externally via IEEE Explore here: https://ieeexplore.ieee.org/document/9755189