This handbook aims to serve as a one-stop, reliable resource, including curated surveys and expository contributions on Federated Learning (FL). It covers a comprehensive range of topics, providing the reader with technical and non-technical fundamentals, applications, and extensive details of various topics. The readership spans from researchers and academics to practitioners who are deeply engaged or are starting to venture into the realms of trustworthy Federated Learning. First introduced in 2016, Federated Learning allows devices to collaboratively learn a shared model while keeping raw data localized, thus promising to protect data privacy. Since its introduction, Federated Learning has undergone several evolutions. Most importantly, its evolution is in response to the growing recognition that its promise of collaborative learning is inseparable from the imperatives of privacy preservation and model security. Federated Learning technology, as a computational framework for multiparty joint modeling, interacts with model parameters through security mechanisms to achieve collaborative training effects. Federated Learning belongs to distributed Machine Learning methods and belongs to the category of privacy computing.

Handbook of Trustworthy Federated Learning (Springer Optimization and Its Applications, 213) PDF

The list of books you might like