Federated Machine Learning: Concept and Applications

TL;DR

This paper reviews federated machine learning, a privacy-preserving approach enabling collaborative model training across organizations with isolated data, and introduces a comprehensive framework including various types and applications.

Contribution

It provides a detailed survey and a unified framework for secure federated learning, expanding beyond initial concepts to include multiple types and practical applications.

Findings

Introduces a comprehensive federated learning framework including horizontal, vertical, and transfer learning.

Surveys existing research and applications in federated learning.

Proposes building data networks among organizations for privacy-preserving knowledge sharing.

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.