A Survey on Federated Learning

Research Topics
FAQ
Publication Ethics
Copyright Infragmentation
[featured_image]
Download
Download is available until [expire_date]
  • Version
  • Download 81
  • File Size 326.68 KB
  • File Count 1
  • Create Date 11/11/2023
  • Last Updated 11/11/2023

A Survey on Federated Learning

A Survey on Federated Learning

Sachin Gupta, Dhananjay Singh, Tanishq Mohite, Aditya Bahiram, Chetan More, Prof. Shital Girme

dept. Computer Engineering) Pune Institute of Computer Technology

Pune, India

 

Abstract—Federated learning (FL) has emerged as an in- triguing model for collaborative machine learning that does not jeopardize data privacy. FL enables the building of robust models while keeping sensitive data localized by permitting distributed training across various devices or servers. This survey paper goes into the world of federated learning, taking an in-depth look at its fundamental concepts, frameworks, and applications. The paper begins with an overview of federated learning, detailing its key ideas and emphasizing its advantages over traditional centralized systems. It then digs into the vast universe of FL frameworks, evaluating their features and contrasting their advantages and disadvantages. The survey covers both open- source and proprietary frameworks, providing information about their applicability for diverse applications.

Index Terms—Federated Learning, Decentralized Machine Learning, Privacy-preserving Machine Learning, Edge Comput- ing, Distributed Learning, Secure Aggregation