Federated Transfer Learning: concept and applications
This is an incremental survey that helps researchers and practitioners understand FTL applications and privacy implications.
The paper addresses the challenge of data isolation in AI development by surveying federated transfer learning (FTL), which enables knowledge transfer across domains with limited overlapping features and users without compromising privacy.
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.