The National Science Foundation (NSF) awarded a $149,990 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) federal grant program to The Trustees of the Stevens Institute of Technology. This award, which runs from January 15, 2025 through December 31, 2026, aims to develop a resilient next-generation (NextG) network design to support federated learning (FL) over mobile devices.
The key project objectives are to: (1) leverage serverless computing at the network edge to efficiently provide machine learning as a service for large-scale, heterogeneous mobile devices supporting FL; (2) design an energy-efficient, privacy-preserving differential privacy mechanism for mobile devices to protect local training data in FL; and (3) develop a multi-bit over-the-air computation based spectrum accessing approach to improve resilience, scalability, and efficiency for transmitting FL model updates under limited spectrum availability. The anticipated outcomes are expected to advance wireless systems and machine learning technologies, while providing multidisciplinary training opportunities for underrepresented students.