CAREER: Towards efficient and fast federated learning in heterogeneous wireless edge networks (NSF-CNS 2145031)

The accelerating penetration of machine learning (ML) based artificial intelligence (AI) in a variety of domains and the explosive growth of wireless applications spur wireless federated learning (WFL), which can achieve collaborative intelligence via federated learning (FL) in wireless edge networks. This project will explore wireless hierarchical federated learning (WHFL), which leverages a hierarchical communication structure to substantially reduce the communication costs of WFL. It will develop fundamental understandings as well as adaptive and efficient algorithms and schemes for WHFL while addressing several unique challenges that have been predominantly unexplored before. This project will study hierarchical FL in wireless edge networks for devices with heterogeneous computation and communication capabilities. The proposed research is motivated by some key insights obtained from our preliminary work: 1) heterogeneous computation configurations, particularly heterogeneous local iteration numbers, have non-trivial impacts on the learning accuracy and learning cost of FL; 2) time-sharing based communication resource allocation is more efficient than bandwidth-sharing, while it results in non-trivial coupling between computation configuration and communication scheduling; 3) global model communication and aggregation have non-trivial impacts when devices have heterogeneous computation configurations. The research outcomes of this project have the potential to enable intelligent control and management of wireless networks, and also support various emerging AI applications over wireless networked systems, such as connected and autonomous vehicles, and collaborative robots.

RET Site: Project-based learning for rural Alabama STEM middle school teachers in machine learning and robotics (NSF-CNS 2206977)

The project will provide unique and holistic research experiences for 30 middle school math and science teachers in the 7th-8th grades from underserved rural areas of Alabama, particularly the Alabama Black Belt region, via a 6-week summer program and 9-month academic year follow-up in each year. The research focus is on mobile robots enabled by cutting-edge technologies like machine learning and artificial intelligence. The goals of the site are to equip teachers with knowledge and skills in robotics and ML/AI and promote their interests in these areas and facilitate teachers’ development and implementation of engaging project-based curricular modules for their classrooms. The site has five primary objectives to reach its goals of providing a rigorous and engaging RET experience: 1) provide education and training activities on the fundamentals of robotics and ML/AI, and a novel platform for research and education of ML-based mobile robots; 2) engage teachers in hands-on research projects on ML-based mobile robots that match well with faculty mentors? active research projects; 3) allow teachers to collaborate with engineering and STEM education faculty to develop the project-based curricular modules; 4) foster teachers’ leadership and pedagogical skills via teacher leader academies and practice of teaching the RET curricular modules; 5) assist teachers to implement the RET curricular modules via academic follow-up.

CCSS: Quality-aware distributed computation for wireless federated learning: Channel-aware user selection, mini-batch size adaptation, and scheduling (NSF-CCSS 2121215)

With the explosive growth of ML/AI technologies, there is enormous potential to advance networking technologies to enable distributed ML/AI data analytics over networked systems. This project will explore innovative cross-disciplinary research at the intersections of wireless networking and machine learning, and study wireless federated learning (WFL) for achieving collaborative intelligence in wireless networks. It will advance the fundamental understanding of quality-aware dynamic distributed computation and computation-communication co-design for WFL. This project will study quality-aware distributed computation for WFL, with focuses on channel-aware user selection, communication scheduling, and adaptive mini-batch size design. The proposed research is built on the key observation that the learning accuracy of the trained model in FL depends heavily on dynamic selection of users participating in the learning process and the quality of their local model updates (which is determined by their mini-batch sizes). The quality of local updates can be treated as a design parameter and used as a knob for adaptive control across users and over time based on users’ communication and computation costs as well as capabilities. This project will spur a new line of thinking and provide new insights to support various emerging ML/AI applications over wireless networked systems, such as collaborative robotics, multi-user mixed reality, and intelligent control and management of wireless networks.