Название: Federated and Transfer Learning
Автор: Roozbeh Razavi-Far, Boyu Wang, Matthew E. Taylor, Qiang Yang
Издательство: Springer
Год: 2023
Страниц: 371
Язык: английский
Формат: pdf (true)
Размер: 12.9 MB

This book provides a collection of recent research works on learning from decentralized data, transferring information from one domain to another, and addressing theoretical issues on improving the privacy and incentive factors of Federated Learning (FL) as well as its connection with transfer learning and Reinforcement Learning. Over the last few years, the Machine Learning (ML) community has become fascinated by federated and transfer learning. Transfer and federated learning have achieved great success and popularity in many different fields of application. The intended audience of this book is students and academics aiming to apply federated and transfer learning to solve different kinds of real-world problems, as well as scientists, researchers, and practitioners in AI industries, autonomous vehicles, and cyber-physical systems who wish to pursue new scientific innovations and update their knowledge on federated and transfer learning and their applications.

This book aims to serve two related goals. First, the book provides high-level background information that will allow students, researchers, and practitioners to quickly get up to speed in these exciting areas, understanding what has been done, how the algorithms work, how they are related, and what are some of the important open problems. Second, the book showcases novel contributions over state of the art, providing significant contributions to the field. We hope that these individual contributions can not only be used directly, but also serve as starting points for completely novel research.

After an introductory chapter, Chaps. 2–4 provide introductions to Federated Learning. Chapters 5–8 then launch into novel federated learning methods. Chapters 9–15 focus on transfer learning, broken down into three chapters on novel transfer learning research,one chapter devoted to a released transfer learning tool,one chapter related to transfer in reinforcement learning, one chapter surveying transfer in reinforcement learning settings, and one chapter focuses on federated transfer reinforcement learning.