Federated Machine Learning: Concept and Applications

By Q. Yang et al.

Published on Feb. 10, 2019

Read the original document by opening this link in a new tab.

Table of Contents

1. INTRODUCTION
2. AN OVERVIEW OF FEDERATED LEARNING
2.1 Definition of Federated Learning
2.2 Privacy of Federated Learning
2.2.1 Indirect information leakage
2.3 A Categorization of Federated Learning
2.3.1 Horizontal Federated Learning
2.3.2 Vertical Federated Learning
2.3.3 Federated Transfer Learning

Summary

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.