Description
Book SynopsisThis 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 as well as its connection with transfer learning and reinforcement learning. Over the last few years, the machine learning 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.
Table of ContentsAn Introduction to Federated and Transfer Learning.- Federated Learning for Resource-Constrained IoT Devices: Panoramas and State of the Art.- Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms.- Cross-silo Federated Neural Architecture Search for Heterogeneous and Cooperative Systems.- A Unifying Framework for Federated Learning.- A Contract Theory based Incentive Mechanism for Federated Learning.- A Study of Blockchain-based Federated Learning.- Swarm Meta Learning.- Rethinking Importance Weighting for Transfer Learning.- Transfer Learning via Representation Learning.- Modeling Individual Humans via a Secondary Task Transfer Learning Method.- From Theoretical to Practical Transfer Learning: The Adapt Library.- Lyapunov Robust Constrained-MDPs for Sim2Real Transfer Learning.- A Study on Efficient Reinforcement Learning Through Knowledge Transfer.- Federated Transfer Reinforcement Learning for Autonomous Driving.
