Fall 2025: Advanced Machine Learning [ CS782 ]
Learning with Graphs


General Description
Graphs are a powerful representation for modeling complex systems of interacting entities, from molecules and proteins to social networks, financial transactions, and knowledge bases. This course explores modern methods for learning with graphs. A variety of topics will be discussed, including graph embeddings and representation learning, graph neural networks, knowledge graphs, large language models and graphs, graphRAG, dynamic graphs. Learning problems will span node classification, link prediction, graph classification, and graph generation.

Through thorough discussion of seminal and recent research papers and a hands-on course project, students will gain a deep understanding of the principles and architectures underlying graph learning, as well as their connections to broader machine learning and deep learning frameworks.

Course Format
Lectures by the instructor and presentations of papers by students.

Classroom Specifics
Attendance is required.

Communication
We use Piazza for communication, and to enable questions and students' discussions. Class material, handouts, and grades are posted on Canvas.

Grading Policy
Grading will be based on quizzes, research paper presentations, in-class activities and participation, and a project. Any deviation from the course policy will be considered a violation of the GMU Honor Code.

Grade Breakdown
Quizzes: 20%
Research paper presentations: 30%
In-class activities and participation: 10%
Project: 40%
Grading Schema
(the threshold may be adjusted for certain grades to take into account the performance of the class as a whole)

Letter Grade Score Range
A+ >=98
A [95, 98)
A- [90, 95)
B+ [85, 90)
B [80, 85)
B- [75, 80)
C+ [70, 75)
C [65, 70)
C- [60, 65)
F <60
Honor Code
This class enforces the GMU Honor Code and the more specific honor code policy special to the Department of Computer Science. You will be expected to adhere to this code and policy.

AI Tools Policy
Students are forbidden from asking any AI tool to solve any of the problems or write any code for this class. This includes solving homework problems, quiz and exam questions, implementing an algorithm, writing reports and solutions. Students are forbidden to upload or paste any assignment material into an AI tool. Students may only ask an AI tool the same sort of general questions they would ask a peer. For the purpose of the Computer Science Department's Honor Code, an AI tool is considered "someone else" who is not an instructor or teaching assistant.

Common policies affecting all courses
Students are required to review the Mason policies affecting all courses.

Disabilities
If you have a documented learning disability or other condition which may affect academic performance, make sure this documentation is on file with the Office of Disability Services and talk to me about accommodations.