Federated Learning: Foundations and Applications provides a comprehensive guide to the foundations, architectures, systems, security, privacy, and applications of federated learning. Sections cover fundamental concepts, including machine learning, deep learning, centralized learning, and distributed learning processes. The book then progresses to coverage of the architectures, algorithms, and system models of Federated Learning, as well as security, privacy, and energy-efficiency techniques. Finally, the book presents various applications of Federated Learning through real-world case studies, illustrating both centralized and decentralized Federated Learning.

Federated Learning has become an increasingly important machine learning technique because it introduces local data analysis within clients and requires exchange of only model parameters between clients and servers, hence the addition of this new release is ideal for those interested in the topics presented.

• Includes detailed discussions on the architectures, algorithms, and applications of Federated Learning
• Covers advanced optimization techniques for Federated Learning algorithms to improve the efficiency and effectiveness of decentralized learning systems
• Provides coverage of high-level Federated Learning security architectures such as FedBoxGuard, which targets single-controller SDN setups by placing “white boxes” between the data and control planes, and FedLiV, which tackles the non-IID data problem by using heterogenous models
• Includes coverage of advanced techniques such as Differential Privacy, Hindmarsh-Rose encryption, and Poisson Binomial Mechanism Vertical Federated Learning (PBM-VFL), a communication-efficient Vertical Federated Learning algorithm with Differential Privacy guarantees