Distributed and Decentralized Artificial Intelligence over Resource-Constrained Edge Devices
Prof. Hülya Seferoğlu
University of Illinois Chicago
Date/Time: Friday, February 7, 2025 at 16:00-17:00 TSI
Place: EE 517 (in-person)
Abstract: A massive amount of data is generated at edge networks with emerging self-driving cars, drones, robots, smartphones, wireless sensors, smart meters, and health monitoring devices. This vast data is expected to be processed via artificial intelligence and machine learning (AI/ML) algorithms, which is extremely challenging over resource-constrained edge devices. The first part of the talk will present our work on communication-efficient distributed and decentralized federated learning at the edge. Next, we will switch our focus to model-distributed inference (MDI), which advocates that an ML model could be partitioned and distributed across multiple devices. These partitions are processed in parallel to reduce the ML inference time. In this context, our work focuses on adaptive, resilient, multi-source, and privacy-preserving MDI solutions.
Biography: Hulya Seferoglu is a Professor in the Electrical and Computer Engineering Department of the University of Illinois Chicago (UIC). She received a B.S. degree in Electrical Engineering from Istanbul University, an M.S. degree in Electrical Engineering and Computer Science from Sabanci University, and a Ph.D. in Electrical and Computer Engineering from the University of California, Irvine. Before joining UIC, she worked as a Postdoctoral Associate in the Laboratory of Information and Decision Systems (LIDS) at the Massachusetts Institute of Technology (MIT). She was a summer intern at AT&T Labs Research, Docomo USA Labs, and Microsoft Research. She was associate editor for IEEE Transactions on Mobile Computing (2022-2024) and IEEE/ACM Transactions on Networking (2017–2021). She received the NSF CAREER award in 2020.