Название: Federated Learning: Principles, Paradigms, and Applications
Автор: Jayakrushna Sahoo, Mariya Ouaissa, Akarsh K. Nair
Издательство: Apple Academic Press, CRC Press
Год: 2025
Страниц: 353
Язык: английский
Формат: pdf (true)
Размер: 17.4 MB

This new book provides an in-depth understanding of Federated Learning, a new and increasingly popular learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. The volume explores how Federated Learning (FL) integrates AI technologies, such as blockchain, Machine Learning, IoT, edge computing, and fog computing systems, allowing multiple collaborators to build a robust Machine Learning model using a large dataset. It highlights the capabilities and benefits of Federated Learning, addressing critical issues such as data privacy, data security, data access rights, and access to heterogeneous data.

The volume first introduces the general concepts of Machine Learning and then summarizes the Federated Learning system setup and its associated terminologies. It also presents a basic classification of FL, the application of FL for various distributed computing scenarios, an integrated view of applications of software-defined networks, etc. The book also explores the role of Federated Learning in the Internet of Medical Things systems as well.
The book provides a pragmatic analysis of strategies for developing a communication-efficient Federated Learning system. It also details the applicability of blockchain with Federated Learning on IoT-based systems. It provides an in-depth study of FL-based intrusion detection systems, discussing their taxonomy and functioning and showcasing their superiority over existing systems.

The book is unique in that it evaluates the privacy and security aspects in Federated Learning. The volume presents a comprehensive analysis of some of the common challenges, proven threats, and attack strategies affecting FL systems. Special coverage on protected shot-based Federated Learning for facial expression recognition is also included.

This comprehensive book, Federated Learning: Principles, Paradigms, and Applications, will enable research scholars, information technology professionals, and distributed computing engineers to understand various aspects of Federated Learning concepts and computational techniques for real-life implementation.

The book contains 12 chapters that provide an in-depth understanding of Federated Learning, which will aid FL enthusiasts and researchers in understanding and applying technology to various actions and further research.

Chapter 1 introduces the general concepts of machine learning. It examines the rationale behind the shift from centralized learning approaches to the decentralized system. Various advancements in distributed learning, along with the introduction of federated learning, are also presented. The growth and technological formation of FL from its preliminary stages are also presented.

Chapter 2 summarizes the federated learning system setup and various terminologies associated with it. It presents a basic classification of FL based on the system architecture, data distribution, and other important categorizations. A comprehensive analysis of the various aggregation approaches based on their types and some of the state-of-the-art approaches are also performed.

Chapter 3 includes studies on the application of FL for various distributed computing scenarios. Implementation and various use cases of FL in edgebased, fog-based, and IoT systems are presented comprehensively. Various challenges associated with the integration are also listed.
...
Chapter 12 focuses on employing protected shot-based Federated Learning for facial expression recognition. Various approaches currently employed for facial recognition are discussed, along with their pitfalls. The need for FL as an effective alternative with its outcomes is also presented as a validation for the work.