This course focuses on machine learning for graph data. Graphs are the universal 
data structures. By representing data as graphs, we can capture entities as well 
as their relationships with each other. Many useful insights can be derived from 
graph-structured data. 

Graph-structured data are ubiquitous and naturally exist in a variety of disciplines 
and application domains ranging from computer science,  social science, economics, 
medicine, to bioinformatics. Example graph data sets include the WWW, social networks, 
biological networks, communication networks, transportation networks, energy grids, 
knowledge graphs and molecular structures. In the real-world, graphs are multi-modal, 
multi-relational, dynamic, large - with many complex patterns - and noisy which can 
pose a problem for effective graph mining and/or learning. 

This course will provide an introduction to recent research in the area of machine 
learning for graphs. The course will survey recent approaches to model graph-structured 
datasets, focusing on fundamental challenges in representation, learning, and inference. 
Classes will consist of instructor presentations, student presentations, and group 
discussions. Students will be required to (1) read, discuss, and present research papers, 
and (2) complete a semester-long class project. Potential projects include: investigating 
the performance of graph ML algorithms, analyzing data with graph ML models, design and 
implementation of graph ML model/algorithm extensions.