Logistics
ACMS 80770-03: Topics in Applied Mathematics: Deep Learning with Graphs, 3 units
Instructor: Navid Shervani-Tabar ([email protected]), 203F Crowley Hall
Lecture: TR 3:30p-4:45p, 231 DeBartolo Hall (or online: notredame.zoom.us/j/5162924029)
Office hours: TR 5:00p-6:00p (TR 5:20p-6:20p from Nov 7), Online: notredame.zoom.us/j/5162924029 or by appointment.
Instructor: Navid Shervani-Tabar ([email protected]), 203F Crowley Hall
Lecture: TR 3:30p-4:45p, 231 DeBartolo Hall (or online: notredame.zoom.us/j/5162924029)
Office hours: TR 5:00p-6:00p (TR 5:20p-6:20p from Nov 7), Online: notredame.zoom.us/j/5162924029 or by appointment.
Course Description
From the emergence of the world wide web to the rise of social media, graphs have been the cornerstone of many revolutionizing advances in the past two decades. This results from graphs’ natural ability to represent the interactions in multi-component systems, such as users in a social network or the amino acids in a protein folding problem. The increased importance of graphs in our daily lives has rendered them a target for machine learning techniques. With AI’s emergence, deep learning methods are becoming the mainstream prediction approach on graphs. This course introduces the fundamental concepts of data analysis and learning on graphs, with an emphasis on generalizing deep neural models to this non-Euclidean domain, with applications to drug discovery, computational biology, recommender systems, and social network analysis. It covers complex data representation with graphs, graph structure and analysis measures, feature extraction from graphs for machine learning models, representation learning approaches, methods for deep learning on graphs, generative graph models, spectral graph theory, and dynamic graphs. Throughout the course, students will build their own deep learning models that will be used to study node, edge, and graph-level learning and investigate benchmark datasets such as citation network. In addition, the course makes use of open source libraries to explore more advanced approaches, validate their own implemented models, and gain experience with software commonly used in science and engineering.
Course Material
Repository: github.com/nshervt/ACMS-80770-Deep-Learning-with-Graphs
Textbooks:
Textbooks:
- Hamilton, William L. Graph Representation Learning. Morgan & Claypool publishers, 2020.
- Newman, Mark. Networks. Oxford university press, 2018.
- Barabási, Albert-László. Network Science. Cambridge university press, 2016.
Grading
- Assignments: 60%
- Final project: 40%
Policies
- Honor Code: This class follows the binding Code of Honor at Notre Dame. Therefore, your graded work in this class must be your own. If collaborations are allowed by the professor for an assignment, make sure to fairly attribute the contribution of other students to your project.
- Office hours: For a productive office hour, students are expected to think through the homework problems and course materials beforehand. Therefore, students should avoid asking generic questions. Instead, they should state their understanding of the problem, show their effort to solve it, and then state where their issue is.
- Masking Policy: Face masks that completely cover the nose and mouth will be worn by all students during the class. Visit covid.nd.edu/policies/masks-policy/.
- Resilience: In the event of an emergency situation or disruption to normal campus operations (weather, health emergency, etc.), our class will likely shift to remote instruction using Zoom, as well as other synchronous and asynchronous course materials. Any changes will be communicated through email and/or Canvas.
- Accommodations: It is the policy and practice of The University of Notre Dame to provide reasonable accommodations for students with properly documented disabilities. Students who have questions are invited to contact Sara Bea Accessibility Services by emailing at [email protected] or by phone at 574-631-7157. Because the University’s Academic Accommodations Processes require students to request accommodations well in advance of the dates they are needed, students are encouraged to contact Accessibility Services at the earliest opportunity. Visit supportandcare.nd.edu/for-students/current-students/accessibility-support/.
- Mental Health: Care and Wellness Consultants provide support and resources to students who are experiencing stressful or difficult situations that may be interfering with academic progress. Through Care and Wellness Consultants, students can be referred to The University Counseling Center (for cost-free and confidential psychological and psychiatric services from licensed professionals), University Health Services (which provides primary care, psychiatric services, case management, and a pharmacy), and The McDonald Center for Student Well Being (for problems with sleep, stress, and substance use). Visit supportandcare.nd.edu.