Federated Machine Learning: Concept and Applications

TLDR

AI faces two major challenges: data isolation across industries and increasing data privacy and security concerns. The authors propose secure federated learning and federated data networks as solutions to these challenges. They present a comprehensive secure federated learning framework extending Google’s 2016 model with horizontal, vertical, and transfer learning, and offer definitions, architectures, applications, and a survey of related work. The survey defines federated learning architectures, applications, and reviews existing work.

Abstract

Today's AI still faces two major challenges. One is that in most industries, data exists in the form of isolated islands. The other is the strengthening of data privacy and security. We propose a possible solution to these challenges: secure federated learning. Beyond the federated learning framework first proposed by Google in 2016, we introduce a comprehensive secure federated learning framework, which includes horizontal federated learning, vertical federated learning and federated transfer learning. We provide definitions, architectures and applications for the federated learning framework, and provide a comprehensive survey of existing works on this subject. In addition, we propose building data networks among organizations based on federated mechanisms as an effective solution to allow knowledge to be shared without compromising user privacy.