AI4OPT Seminar Series
Date: Thursday, February 16, 2023
Time: Noon – 1:00 pm
Location: Instructional Center 115 (Scale Up Room) - (759 Ferst Dr, Atlanta, GA 30318)
Join Virtually: https://gatech.zoom.us/j/99381428980
Speaker: Stefanie Jegelka
Machine Learning for Discrete Optimization: Graph Neural Networks, Generalization Under Shifts, and Loss Functions
Abstract: Graph Neural Networks (GNNs) have become a popular tool for learning algorithmic tasks, related to combinatorial optimization. In this talk, we will focus on the “algorithmic reasoning” task of learning a full algorithm. While GNNs have shown some promising empirical results, their generalization properties are less well understood. We will try to understand out-of-distribution generalization in widely used message passing GNNs, with an eye on applications in learning for optimization: what may be an appropriate metric for measuring shift? Under what conditions will a GNN generalize to larger graphs? In the last part of the talk, we will take a brief look at objective (loss) functions for learning with discrete objects, beyond GNNs. Neural networks work best with continuous, high-dimensional spaces. Can we integrate this into appropriate loss functions?
Talk is based on joint work with Ching-Yao Chuang, Keyulu Xu, Joshua Robinson, Nikos Karalias, Jingling Li, Mozhi Zhang, Simon S. Du, Ken-ichi Kawarabayashi, and Andreas Loukas.
Bio: Stefanie Jegelka is an associate professor in the department of EECS at MIT. Before joining MIT, she was a postdoctoral researcher at UC Berkeley, and obtained her PhD from ETH Zurich and the Max Planck Institute for Intelligent Systems. Stefanie has received a Sloan Research Fellowship, an NSF CAREER Award, a DARPA Young Faculty Award, the German Pattern Recognition Award, a Best Paper Award at ICML and an invitation as sectional lecturer at the International Congress of Mathematicians. She has co-organized multiple workshops on (discrete) optimization in machine learning and graph representation learning and has served as an Action Editor at JMLR and a program chair of ICML 2022. Her research interests span the theory and practice of algorithmic machine learning, particularly learning problems that involve combinatorial structure.
To meet with Stefanie, sign up here: https://docs.google.com/document/d/12E1cVyOuZebDRX-7demH6Tuibar0sIvN/edit?usp=sharing&ouid=112708268997233335091&rtpof=true&sd=true
*To accommodate more people into Stefanie's limited schedule, anyone is welcome to join for breakfast and lunch. Please also consider coordinating with fellow faculty and students to share meeting slots
Lunch will be served at the seminar. So, please stop by 15 minutes before the seminar to pick up lunch.
To receive AI4OPT seminar announcements, please sign up to our mailing list. at https://lists.isye.gatech.edu/mailman/listinfo/ai4opt-seminars.
Past seminars can be found at https://www.ai4opt.org/seminars/past-seminars.