Communication-efficient and client selection for federated learning with label noise correction

Abstract

Federated learning (FL) is becoming a secure machine learning paradigm for many applications which require high privacy protection, such as security, healthcare, and finance. FL gathers the power of available remote low-resource devices to join the training process. As a result, it reduces the computational burden on central servers as well as communication costs. While machine learning and deep learning have achieved impressive results, FL is still in its early stages and must face new challenges which may dramatically degrade the performance of the global model. This project aims to overcome some of the above issues by proposing solutions for FL.

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 16, 2024
Source ID
FA23862314064

Entities

People

  • Thanh-Hai Tran

Organizations

  • Air Force Office of Scientific Research
  • Hanoi University of Science and Technology
  • United States Air Force

Tags

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Cybersecurity.
  • Parallel and Distributed Computing.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks