About the Book:

How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? Traditional machine learning approaches need to combine all data at one location, typically a data center, which may very well violate the laws on user privacy and data confidentiality. Today, many parts of the world demand that technology companies treat user data carefully according to user-privacy laws. The European Union's General Data Protection Regulation (GDPR) is a prime example. In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security, and incentive mechanism design based on economic principles and game theory. We explain different types of privacy-preserving machine learning solutions and their technological backgrounds, and highlight some representative practical use cases. We show how federated learning can become the foundation of next-generation machine learning that caters to technological and societal needs for responsible AI development and application.

Contents:

1.    Introduction

2.    Background

3.    Distributed Machine Learning

4.    Horizontal Federated Learning

5.    Vertical Federated Learning

6.    Federated Transfer Learning

7.    Incentive Mechanism Design for Federated Learning

8.    Federated Learning for Vision, Language, and Recommendation

9.    Federated Reinforcement Learning

10. Selected Applications

11. Summary and Outlook A Legal Development on Data Protection

About the Authors:

Qiang Yang is Chief AI Officer at WeBank and Chair Professor of CSE at HKUST. He is a pioneer in AI, transfer learning, and federated learning, with fellowships in ACM, AAAI, IEEE, IAPR, and AAAS. He has led major editorial boards, served as IJCAI President, co-founded 4Paradigm, and authored several AI books. 

Yang Liu is a Senior Researcher at WeBank, focusing on machine learning, federated learning, and transfer learning. She earned her Ph.D. from Princeton (2012) and holds patents with publications in *Nature* and *ACM TIST*. 

Yong Cheng is a Senior Researcher at WeBank, with expertise in deep learning, federated learning, computer vision, and optimization. He has 20+ publications, 40+ patents, and awards from TU Darmstadt and Zhejiang University. 

Yan Kang is a Senior Researcher at WeBank, specializing in privacy-preserving and federated learning. He earned his Ph.D. from the University of Maryland, worked with NIST/NSF projects, and has industry experience at Stardog Union and Cerner. 

Tianjian Chen is Deputy GM of WeBank’s AI Department, building a federated learning–based Banking Intelligence Ecosystem. Previously, he was Chief Architect at Baidu Finance with 12+ years in distributed systems and machine learning.