Federated Transfer Learning: concept and applications

TL;DR

This paper surveys federated transfer learning, a technique enabling knowledge sharing across diverse domains without compromising privacy, highlighting its applications, background, and privacy considerations.

Contribution

It provides a comprehensive overview of federated transfer learning, including its background, applications, and privacy aspects, filling a gap in existing literature.

Findings

FTL enables knowledge transfer across non-overlapping domains.

Privacy-preserving aspects are crucial in FTL applications.

FTL has diverse applications across industries.

Abstract

Development of Artificial Intelligence (AI) is inherently tied to the development of data. However, in most industries data exists in form of isolated islands, with limited scope of sharing between different organizations. This is an hindrance to the further development of AI. Federated learning has emerged as a possible solution to this problem in the last few years without compromising user privacy. Among different variants of the federated learning, noteworthy is federated transfer learning (FTL) that allows knowledge to be transferred across domains that do not have many overlapping features and users. In this work we provide a comprehensive survey of the existing works on this topic. In more details, we study the background of FTL and its different existing applications. We further analyze FTL from privacy and machine learning perspective.