Federated Learning -- Methods, Applications and beyond
It addresses data privacy and distribution issues for fields like medicine, but is incremental as it offers a review rather than new contributions.
This paper tackles the challenges of data privacy and distributed data in machine learning by providing an overview of Federated Learning methods and applications, including vertical, horizontal, and federated transfer learning, as introduced by Google in 2016.
In recent years the applications of machine learning models have increased rapidly, due to the large amount of available data and technological progress.While some domains like web analysis can benefit from this with only minor restrictions, other fields like in medicine with patient data are strongerregulated. In particular \emph{data privacy} plays an important role as recently highlighted by the trustworthy AI initiative of the EU or general privacy regulations in legislation. Another major challenge is, that the required training \emph{data is} often \emph{distributed} in terms of features or samples and unavailable for classicalbatch learning approaches. In 2016 Google came up with a framework, called \emph{Federated Learning} to solve both of these problems. We provide a brief overview on existing Methods and Applications in the field of vertical and horizontal \emph{Federated Learning}, as well as \emph{Fderated Transfer Learning}.