Image come from resources at the bottom

Course Description

Graph-structured data is ubiquitous worldwide, e.g., social networks like Facebook, e-commerce platforms like Amazon, infrastructures like transportation networks, and chemical graphs like molecules. This course explores basic analytical techniques, computational methods, and graph machine learning models for graph-related applications.

Topics include:

• Graph Foundations: Basic Graph Theory, Statistical Graph Models, Network Properties.
• Graph Computational Methods: Link Prediction, Node/Graph Classification, Diffusion, and Clustering.
• Deep Graph Models: GNNs, Self-supervised Learning, Data Quality and Trustworthy Issues.
• Real-world Applications: Academic Paper Management, Recommender System, Drug Discovery.

Students will complete assigned homework, a midterm exam, and a team-based course project.

Lectures

Tuesday/Thursday, 4:00-5:20 pm, 132 GSH

Office Hours

Instructor: Zoom Meeting

• Friday 3:30-5:00 pm
• By appointment

TA: TBD

Mid-term Exam

Final Project

TDB

Acknowledgement

Note that some of the lectures of this course are borrowed or adapted from the following:

• Social Network Analysis, Tyler Derr's course at Vanderbilt
• Graph Mining and Exploration at Scale: Methods and Applications, Danai Koutra's course at University of Michigan
• Social Network Analysis, Leonid E. Zhukov's course at National Research University Higher School of Economics
• Analysis of Networks, Jure Leskovec's course at Stanford
• Network Science Analytics, Fragkiskos Malliaros's course at CentraleSupelec
• https://graphsandnetworks.com/the-cora-dataset/
• https://arxiv.org/pdf/2109.10703
• https://www.ebme.co.uk/articles/clinical-engineering/functional-magnetic-resonance-imaging-fmri
• https://www.floridamuseum.ufl.edu/science/at-last-butterflies-get-a-bigger-better-evolutionary-tree/
• https://www.researchgate.net/publication/270891688_Identifying_Your_Customers_in_Social_Networks