An Exploration of Federated Learning: Application Scenarios and Technical Implementations

DOI

10.2991/978-94-6463-823-3_106How to use a DOI?

Keywords

Federated Learning; Horizontal Federated Learning; Vertical Federated Learning; Federated Transfer Learning

Abstract

With large-scale rollout of Internet of Things (IoT) appliances, the data at the network edge has expanded exponentially. Conventional centralized learning techniques face challenges such as exposure of privacy and delayed response when dealing with this data. Federated learning, being a decentralized machine learning paradigm, ensures privacy and reduces response time by locally training models and sharing parameters. This paper presents an extensive survey of the three prevailing categories of federated learning. Based on different corresponding papers, we describe their attributes, environments, and technical implementations. Horizontal federated learning (HFL) can be applied to scenarios where data features are the same but samples differ, such as banks among regions, distributed high-speed monitoring image recognition, distributed wind and photovoltaic power forecasting. Vertical federated learning (VFL) applies when data samples are homologous but features are different, such as recommending stations of oil-electric hybrid vehicles and data exchange of the Internet of Things. Federated transfer learning (FTL) is aimed at cross-domain knowledge transfer and can solve problems like rolling bearing fault diagnosis. It is learned that all kinds of federated learning have their own strengths in various conditions but encounters barriers like non-IID data and security of privacy.

Copyright

© 2025 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  - Ziheng Wang
PY  - 2025
DA  - 2025/08/31
TI  - An Exploration of Federated Learning: Application Scenarios and Technical Implementations
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 1103
EP  - 1114
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_106
DO  - 10.2991/978-94-6463-823-3_106
ID  - Wang2025
ER  -