Search the World's Largest Database of Information Science & Technology Terms & Definitions
InfInfoScipedia LogoScipedia
A Free Service of IGI Global Publishing House
Below please find a list of definitions for the term that
you selected from multiple scholarly research resources.

What is Federated Learning

Chapter 8
Multidisciplinary Functions of Blockchain Technology in AI and IoT Applications
Federated learning is a technology to enable distributed client devices to train AI models without sharing the data.
Published in Chapter:
A Blockchain-Based Federated Learning: Concepts and Applications
Ankit Khushal Barai (Department of CSE, Indian Institute of Information Technology, Nagpur, India), Robin Singh Bhadoria (Department of Computer Science and Engineering, Hindustan College of Science and Technology, India), Jyotshana Bagwari (Department of CSE, Uttarakhand Technical University, India), and Ivan A. Perl (ITMO University, Russia)
Copyright: © 2021 |Pages: 20
DOI: 10.4018/978-1-7998-5876-8.ch008
Abstract
Conventional machine learning (ML) needs centralized training data to be present on a given machine or datacenter. The healthcare, finance, and other institutions where data sharing is prohibited require an approach for training ML models in secured architecture. Recently, techniques such as federated learning (FL), MIT Media Lab's Split Neural networks, blockchain, aim to address privacy and regulation of data. However, there are difference between the design principles of FL and the requirements of Institutions like healthcare, finance, etc., which needs blockchain-orchestrated FL having the following features: clients with their local data can define access policies to their data and define how updated weights are to be encrypted between the workers and the aggregator using blockchain technology and also prepares audit trail logs undertaken within network and it keeps actual list of participants hidden. This is expected to remove barriers in a range of sectors including healthcare, finance, security, logistics, governance, operations, and manufacturing.
Full Text Chapter Download: US $37.50 Add to Cart
More Results
Chapter 4
Impact of Digital Twins on Smart Cities: Healthtech and Fintech Perspectives – opportunities, Challenges, and Future Directions
One of the artificial intelligence methods that allows computing without decryption of data.
Published in Chapter: Impact of Digital Twins on Smart Cities: Healthtech and Fintech Perspectives – opportunities, Challenges, and Future Directions; From: Impact of Digital Twins in Smart Cities Development
Full Text Chapter Download: US $37.50 Add to Cart
Chapter 10
The Value Proposition of Machine Learning in Construction Management: Exploring the Trends in Construction 4.0 and Beyond
A machine learning approach where no data exchange is necessary, as it is based on local data samples, stored across multiple decentralized edge devices or servers.
Published in Chapter: The Value Proposition of Machine Learning in Construction Management: Exploring the Trends in Construction 4.0 and Beyond; From: Artificial Intelligence and Machine Learning Techniques for Civil Engineering
Full Text Chapter Download: US $37.50 Add to Cart
Chapter 10
Suggesting New Techniques and Methods for Big Data Analysis: Privacy-Preserving Data Analysis Techniques
This approach enables the creation of a shared model from multiple decentralized data sources, like smartphones or computers, without transferring the data itself. It enhances privacy by keeping sensitive data localized while allowing collective learning and model improvement from diverse datasets.
Published in Chapter: Suggesting New Techniques and Methods for Big Data Analysis: Privacy-Preserving Data Analysis Techniques; From: Big Data Analytics Techniques for Market Intelligence
Full Text Chapter Download: US $37.50 Add to Cart
Chapter 4
AI-Based Wireless Communication
It is decentralized approach employed at the edge nodes which learns global model collaboratively using local data sets. It is basically a distributed training technique.
Published in Chapter: AI-Based Wireless Communication; From: Challenges and Risks Involved in Deploying 6G and NextGen Networks
Full Text Chapter Download: US $37.50 Add to Cart
Chapter 9
Digital Twins and Federated Learning for Smart Cities and Their Applications
Federated learning is a machine learning technique that allows machine learning models to obtain experience from different data sets placed in different sites (e.g., local data centers, a central server) deprived of sharing training data. This allows personal data to remain in local sites, reducing possibility of personal data breaches. Federated learning is used to train other machine learning algorithms by using multiple local datasets without exchanging data. This allows companies to create a shared global model without putting training data in a central location.
Published in Chapter: Digital Twins and Federated Learning for Smart Cities and Their Applications; From: Demystifying Federated Learning for Blockchain and Industrial Internet of Things
Full Text Chapter Download: US $37.50 Add to Cart
Chapter 11
Challenges of Developing AI Applications in the Evolving Digital World and Recommendations to Mitigate Such Challenges: A Conceptual View
This is a machine learning technique that trains an algorithm on the decentralised data existing on different edge devices than compared to the traditional method of accumulating the data. This model was developed by Google and is an evolving technique that ensures data security.
Published in Chapter: Challenges of Developing AI Applications in the Evolving Digital World and Recommendations to Mitigate Such Challenges: A Conceptual View; From: Confluence of AI, Machine, and Deep Learning in Cyber Forensics
Full Text Chapter Download: US $37.50 Add to Cart
eContent Pro Discount Banner
InfoSci OnDemandECP Editorial ServicesAGOSR