Federated Learning over Edge-Fog-Cloud Architectures for Distributed Intelligence

DOI

10.2991/978-94-6239-697-5_23How to use a DOI?

Keywords

Federated Learning; Edge Computing; Fog computing; Cloud computing; Distributed Intelligence; Internet of things; (IoT); Privacy-preserving learning

Abstract

The high rate of Internet of Things (IoT) device growth has led to massive amounts of distributed data being created at the network edge, much of which is highly sensitive data about users. Traditional centralized machine learning models rely on aggregation of the raw data in a cloud server, which raises serious privacy, legal, communication, and latency concerns. Such restrictions have encouraged the development of federated learning (FL), a distributed machine learning model that enables collaborative model training while keeping raw data on the user devices. Meanwhile, the current computing infrastructures are shifting from a cloud-only model to encompass a continuum of edge, fog, and cloud computing. This hierarchy architecture supports low latency processing, optimized use of resources, and scalable coordination of distributed intelligence. Federated learning with an edge-fog-cloud architecture represents a beneficial solution to privacy-preserving, scalable, and real-time intelligent systems, especially in large-scale IoT and Industrial IoT systems. The paper explores federated learning on an edge-fog-cloud-based system in distributed intelligence. The key goals include the analysis of the architectural functions of edge, fog, and cloud layers in federated learning, the exploration of the communication-computation trade-offs, and the emphasis on the fact that hierarchical aggregation enhances the scale and efficiency. This study provides a systematic foundation for developing next-generation smart applications, which need safe, scalable, and privacy-conscious collaborative learning along the edge-fog-cloud spectrum.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shairy Shairy
AU  - Rachit Garg
PY  - 2026
DA  - 2026/06/04
TI  - Federated Learning over Edge-Fog-Cloud Architectures for Distributed Intelligence
BT  - Proceedings of the Conference on Bridging Engineering Disciplines with AI and Machine Learning (BEDAIML 2026)
PB  - Atlantis Press
SP  - 270
EP  - 279
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-697-5_23
DO  - 10.2991/978-94-6239-697-5_23
ID  - Shairy2026
ER  -