Date of Award
Spring 5-7-2021
Degree Type
Thesis
Degree Name
Master of Science in Software Engineering
Department
Software Engineering and Game Design and Development
Committee Chair/First Advisor
Dr.Yan Huang
Second Advisor
Dr. Joy Li
Abstract
The advent of machine learning techniques has given rise to modern devices with built-in models for decision making and providing rich content to users. This typically involves processing huge volumes of data in central servers and sending updated models to end-user devices. There are two main concerns on this server architecture, one is the privacy of data that is being transferred to a central server and the other is volumes of data sent over the network for the model update. Federated Learning helps solve these problems by training models on local data within the device and aggregating the model with other devices. Federated Learning involves a central server for the aggregation and the resulting updates to the clients, here only model parameters are shared with the central server not the data itself thereby preserving privacy. But all the applications are not being compatible with Federated Learning and also there is a privacy concern of models being shared to the central server which can be susceptible to malicious attacks. In this paper, central server free Federated Learning, which is decentralized Federated Learning is used, where the parameters will be exchanged between the clients one to one and get their models updated removing the need for a central server for aggregation. Peer-to-peer techniques are used for communicating between clients and different node architectures to achieve better accuracy. This happens when the clients meet another client in a connected social network environment. The results show that the communication happens between clients in a decentralized fashion and thereby achieving privacy in a more trusted manner.