ECE Department Seminar
Federated Edge Learning: Advances and Challenges
Mohammad Mohammadi Amiri, Ph.D.
Postdoctoral Research Associate
Thursday, February 25, 2021
10:00 am – 11:00 am
Zoom Meeting Link:
Abstract: Today wireless devices generate a tremendous amount of valuable data that can be utilized to improve the intelligence of many applications. Due to the growing storage and computational capabilities of wireless edge devices, it is increasingly
attractive to store and process the data locally by shifting network intelligence to the edge. In contrast to traditional machine learning solutions, it is not desirable to offload such massive amounts of data available at the wireless edge devices to a cloud
server for centralized processing due to latency, bandwidth, and power constraints in wireless networks, as well as privacy concerns of users. Federated learning has emerged as a privacy-enhancing approach that can exploit the local data generated by the wireless
devices and their processing capabilities to make inferences about the state of a system, while the local data never leaves the devices. In this talk, I highlight the advances and challenges of developing a federated learning framework while incorporating
physical layer aspects of wireless networks with limited resources into the system design, and provide rigorous analytical results to understand the impact of the underlying communication channels and protocols on the system performance.
Bio: Mohammad received the B.Sc. and M.Sc. degrees in Electrical Engineering from the Iran University of Science and Technology in 2011 and the University of Tehran in 2014, respectively, both with highest rank in classes. He also obtained his Ph.D.
degree at Imperial College London in 2019. He is the recipient of the Best Ph.D. Thesis award from both the IEEE Information Theory Chapter of UK and Ireland and the Department of Electrical and Electronic Engineering at Imperial College London in the year
2019. He is currently a Postdoctoral Research Associate in the Department of Electrical Engineering at Princeton University. His research interests include machine learning, information and coding theory, wireless communications, privacy and security, distributed
computing, and signal processing.