Student Work

Federated Learning

Public

Downloadable Content

open in viewer

Federated learning, training machine learning models on individual user data and aggregating the models, is a rapidly expanding field that focuses on user privacy. It provides the convenience of machine learning with additional privacy. In the computer science portion of this MQP, we evaluate and compare two federated learning algorithms and show that under various circumstances, FedProx outperforms FedAvg in identically and independently distributed scenarios. In non-identically and independently distributed scenarios, the relative performance of the algorithms is less predictable. In the professional writing portion of this MQP, one team member identifies best practices for describing machine learning in medical contexts.

  • This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
Creator
Subject
Publisher
Identifier
  • 22921
  • E-project-050621-124135
Advisor
Year
  • 2021
Date created
  • 2021-05-06
Resource type
Major
Rights statement
Last modified
  • 2021-08-28

Relations

In Collection:

Items

Items

Permanent link to this page: https://digital.wpi.edu/show/rn3014435