Doctoral Thesis: A Practical Approach to Federated Learning

Monday, April 25
9:00 am

On zoom, see below

Vaikkunth Mugunthan

Machine learning models benefit from large and diverse training datasets. However, the sensitivity of the data and government regulations such as GDPR, HIPPA, and CCPA restrict how organizations can share data with other entities. As such, entities with sensitive datasets can only develop locally optimal models. Federated learning (FL) facilitates robust machine learning by enabling the development of global models without sharing sensitive data. However, there are two broad challenges associated with FL: privacy challenges and training/performance-related challenges. Privacy challenges pertain to attacks that reveal sensitive information on local client data. Training/Performance-related challenges include high communication costs, data heterogeneity across clients, and lack of personalization techniques. All these concerns have to be addressed to make FL practical, scalable, and useful. In this talk, I discuss my various contributions to FL including DynamoFL, an easy-to-use production-level system for FL, and show how I address these challenges.


  • Date: Monday, April 25
  • Time: 9:00 am
  • Location: On zoom, see below
Additional Location Details:

Thesis Supervisor: Dr. Lalana Kagal

Thesis Committee: Professors Polina Golland and Samuel Madden