π§ Graph Learning from Smooth Signals and Regressors (GLReg)
How do we learn the underlying structure of a graph when signals are both smooth and influenced by covariates?
Join Dr. Jing Guo as she presents a novel graph learning framework that combines: - Smoothness of signals on nodes - Linear regression using node-level predictors
This model (GLReg) enables the inference of graph topology using real-world, noisy data and can be applied to domains like: - π Geographical data
- 𧬠Biomedical networks
- π§βπ€βπ§ Social networks
π What Youβll Learn
- How to infer a graph Laplacian from both response and predictor signals
- The interaction between smooth signals and regressors
- Applications using both simulated and real-world data
π
Date: March 28, 2025
π Time: 1:30 pm - 2:00 pm π Venue: Holt Hall 291
π Pre-Seminar Materials
Participants are encouraged to review the materials in advance:
- π Graph Learning From Signals With Smoothness Superimposed by Regressors (2023)
Bring questions β weβre here to learn together!
