Award Date

5-1-2021

Degree Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Computer Science

First Committee Member

Mingon Kang

Second Committee Member

Kazem Taghva

Third Committee Member

Fatma Nasoz

Fourth Committee Member

Jeehee Lee

Number of Pages

42

Abstract

With the onset of the digital era, data privacy is one of the most predominant issues. Decentralized learning is becoming popular as the data can remain within local entities by maintaining privacy. Federated Learning is a decentralized machine learning approach, where multiple clients collaboratively learn a model, without sharing raw data. There are many practical challenges in solving Federated Learning, which include communication set up, data heterogeneity and computational capacity of clients. In this thesis, I explore recent methods of Federated Learning with various settings, such as data distributions and data variability, used in several applications. In addition, I, specifically, examine a design of systematic network topology in a federated framework with computational experiments.

Keywords

Federated Learning; Data distribution; Data privacy; Machine learning; Analysis

Disciplines

Computer Sciences

File Format

pdf

File Size

2900 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Rights

IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/

Download


Share

COinS