Seminar by Prof. Ang Li: Enable Edge Intelligence via Scalable and Efficient Federated Learning

The proliferation of edge devices and the gigantic amount of data they generate are distributed everywhere. Such distributed data fuel the intelligence at the edge where data reside. In this talk, I will present our research on how to enable intelligence on large-scale edge devices by leveraging the power of federated learning. In particular, I present our recent works on jointly optimizing the communication and computation cost of federated learning, personalization of federated learning, and automated hyperparameter optimization in federated learning. Additionally, I will also discuss the challenges and opportunities of federated learning in the era of large Al models. Room: 4105, Bldg: Brendan Iribe Center for Computer Science and Engineering, 8125 Paint Branch Dr, College Park, Maryland, United States, 20740, Virtual: https://events.vtools.ieee.org/m/391114