Virginia Tech® home

Seminar: Opportunistic and Decentralized Learning in the Internet of Things

Christine Julien

Professor and Department Head, Computer Science
Virginia Tech


Friday, September 6, 2024
2:30 - 3:45PM
3100 Torgersen Hall

 

Abstract


Smartphones, wearables, and embedded devices that define the Internet of Things are ubiquitous in our environments, and they are increasingly complex in their sensing, computation, and communication capabilities. In addition, these devices regularly generate (and distribute) vast quantities of potentially personal data that can be used to build sophisticated machine learning models. In this talk, I will present the work of my research group over the past five years in the area of opportunistic collaborative learning (OppCL), a form of decentralized learning that relies solely on device-to-device exchanges between devices that encounter one another. In OppCL, devices learn through these encounters and through on-device training without the aid of any centralized infrastructure. This talk will present the motivation and use cases behind OppCL and several of our research contributions related to formalizing the learning process and building systems that effectively and efficiently implement the OppCL learning architecture. The talk will close with a look forward into open challenges in employing OppCL for diverse emerging Internet of Things applications.

Biography

Dr. Christine Julien is a professor and department head in the Department of Computer Science at Virginia Tech. She joined the department in August of 2024 after spending 20 years at the University of Texas at Austin. In that time, her research has focused on the intersection of software engineering and dynamic, unpredictable networked environments. Her specific focus is on the development of models, abstractions, tools, and middleware whose goals are to ease the software engineering burden associated with building applications for pervasive and mobile computing environments. Dr. Julien's research has been supported by the National Science Foundation (NSF), the Air Force Office of Scientific Research (AFOSR), the Department of Defense, Google, Tektronix, and Toyota.