« All Events
Room 1163 Mechanical Engineering
A critical change is happening in today’s Internet of Things (IoT). The computational power atthe edge device is steadily increasing. AI chips are rapidly infiltrating the market. Mobile phones’processing power is becoming comparable to laptops available for everyday use. Tesla’s autopilot systemhas 150 million times more computing power than Apollo 11, and small local computers such as Raspberry Pis have become commonplace in manufacturing systems. This change opens a new paradigm of dataanalytics within IoT, one that exploits edge compute resources to process more of users’ data where it’screated. More specifically, with the availability of some computing resources at each client, clients canexecute small computations locally, instead of sharing all raw data to a central cloud, and then only sharethe minimum information needed to collaboratively extract knowledge and build smart analytics whilekeeping their personal data stored locally. This paradigm shift sets forth many intrinsic advantages,including privacy, cost-effectiveness, diversity, fairness, and reduced computation and latency, amongmany others. In this talk, I term this future of IoT as the “Internet of Federated Things (IoFT)” and discussour recent efforts in federated data analytics aimed at bringing this future into reality. Specifically, I willpresent federated analytics approaches to tackle three central challenges within IoFT: (1) Personalization:where participants borrow strength from each other yet retain their own individualized models. (2)Fairness: to allow solutions with good representation power across groups of heterogeneous participants(3) Distributed uncertainty quantification (UQ): where we bring federated analytics to correlatedparadigms beyond empirical risk minimization to quantify uncertainty. I end the talk by describing ourprototyping efforts to generate real-life IoFT data
Bio: Raed Al Kontar is an assistant professor in the Industrial & Operations engineering department at theUniversity of Michigan and an affiliate with the Michigan Institute for Data Science. Raed’s researchfocuses on distributed and federated probabilistic modeling. Raed obtained an undergraduate degree incivil & environmental engineering and mathematics from the American University of Beirut in 2014followed by a master’s degree in statistics in 2017 and a Ph.D. degree in Industrial & System Engineeringin 2018, both from the University of Wisconsin-Madison. Raed has seven best paper awards from theINFORMS Quality, Statistics & Reliability section, INFORMS Data Mining section, and IISE. Raed receivedthe NSF CAREER award in 2022. His research is currently supported by both NSF and NIH.