Federal Grant Award Summary

Texas A&M University received a $514,038 Project Grant from the National Science Foundation's Division of Computer and Network Systems under the Computer and Information Science and Engineering program (CFDA 47.070), awarded October 1, 2025, with completion targeted for September 30, 2026. The grant supports a CAREER-track research initiative focused on developing a novel federated learning (FL) framework that enables Internet-of-Things (IoT) devices at the wireless edge to collaboratively train machine learning models while preserving data privacy and meeting latency requirements of delay-sensitive applications. The research addresses limitations of cloud-based federated learning by processing data locally at mobile edge networks rather than transmitting to distant cloud servers.

The project encompasses three interconnected research thrusts: (1) design of network-aware learning algorithms optimized for decentralized IoT data training over wireless edge networks; (2) joint optimization of resource allocation and model learning using deep reinforcement learning to improve accuracy under system heterogeneity and resource constraints; and (3) development of differential privacy techniques to protect personal data on IoT devices. The initiative targets applications including augmented reality, autonomous driving, mobile healthcare, and smart manufacturing. The award includes an educational agenda incorporating K-12 outreach through summer camps for high school teachers, mentorship of undergraduate and graduate students from underrepresented groups, and dissemination of research findings through course development and industry seminars.