This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) provides $150,000.00 to the University of Houston System to develop a resilient next-generation (NextG) network design for federated learning over mobile devices.
The key products and services to be delivered include:
Exploiting serverless computing at the network edge to efficiently provide machine learning as a service to support federated learning over large-scale heterogeneous mobile devices.
Proposing an energy-efficient differential privacy mechanism for mobile devices to protect the privacy of local training data used in federated learning.
Developing a multi-bit over-the-air computation based spectrum accessing design to improve spectrum efficiency, network scalability, and energy consumption for mobile devices in federated learning applications.
The award period runs from January 1, 2025 to December 31, 2026. The proposed innovations are expected to enrich knowledge of wireless systems and machine learning, while also providing multidisciplinary training opportunities for underrepresented students.