- Instructor: William L. Hamilton
- Email: firstname.lastname@example.org
- Office hours: Mondays 2:30-4:30pm
- Term: Winter 2020
- When: Mondays and Wednesdays, 1:05-2:25pm
- Where: Zoom Meeting ID 6957556003
Note that the syllabus has been adapted in response to the COVID-19 pandemic. The original syllabus can be viewed here.
Graph representation learning (GRL) is a quickly growing subfield of machine learning that seeks to apply machine learning methods to graph-structured data. Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. This course will provide an introduction to graph representation learning, including matrix factorization-based methods, random-walk based algorithms, graph neural networks, and deep generative models of graphs. During the course, we will study both the theoretical motivations (e.g., from spectral graph theory) and practical applications of these methods.
Course content (subject to minor changes):
- Basics of network and graph analysis
- Link prediction
- Graph and node classification
- Spectral clustering
- Node embeddings
- Knowledge graph embeddings
- Graph neural networks
- Graph signal processing
- Deep generative models of graphs
- Applications in computational biology and NLP
Reference MaterialsThere is no required textbook. Lecture notes and references will be available from the schedule on the course web page.
Prerequisites / Anterequesites
Basic knowledge of a programming language is required (ideally Python). Knowledge of probabilities/statistics, calculus and linear algebra is required. Example courses at McGill providing sufficient background in probability are MATH-323 or ECSE-305. Machine learning background, as provided for example by COMP-551 or COMP-652 is required. If you have doubts regarding your background, please contact Will to discuss it.
The courses is intended for hard-working, technically skilled, highly motivated students. Participants will be expected to display initiative, creativity, scientific rigour, critical thinking, and good communication skills.
Evaluation CriteriaThe class grade will be based on the following components:
- Paper presentation - 15%
- Project proposal - 5%
- Project final report - 70%
- Peer reviews - 5%
- Participation - 5%
Prior to March 30th, lectures consisted of a background lecture by Prof. Hamilton followed by in-class paper presentations by students. Starting March 30th, lectures consist entirely of content delivered by Prof. Hamilton, with recorded presentations by students on related papers being made available weekly. The presented papers will be previously published (not by the students) and related to the topic of the lecture. The presentations will be 12-13 minutes. Slides are strongly recommended for the presentations, and recorded presentations should make use of the record feature in Zoom, PowerPoint, and/or Keynote. Recorded presentations will be sent by email to Prof. Hamilton by the deadline indicated in this spreadsheet. Students will be graded on the quality of their presentation.
This is a project-based course and will involve a substantial original research project, which will be completed in groups of 2-3. All students in a group will receive the same grade. Students are permitted to undertake a research project that is related to their thesis or other external research projects, but the work done for the course must represent substantial additional work and cannot be submitted for grades in another course.
Students will submit peer reviews of other students' work. Peer reviews of a piece of work will not be used to determine that work's grade. However, students will be graded on the quality of the reviews *they provide*.
Evaluation PolicyAll course work should be submitted online (details to be given in class) on the assigned due date. Late work will be automatically subject to a 20% penalty and can be submitted up to 3 days after the deadline.
Some of the course work will be individual, other components can be completed in groups. It is the responsibility of each student to understand the policy for each work, and ask questions of the instructor if this is not clear. It is also the responsibility of each student to carefully acknowledge all sources (papers, code, books, websites, individual communications) using appropriate referencing style when submitting work.
We will use automated systems to detect possible cases of text or software plagiarism. Cases that warrant further investigation will be referred to the university disciplinary officers. Students who have concerns about how to properly use and acknowledge third-party software should consult the course instructor or TAs.
McGill University values academic integrity. Therefore all students must understand
the meaning and consequences of cheating, plagiarism and other academic offences
under the Code of Student Conduct and Disciplinary Procedures (see
In accord with McGill University's Charter of Students' Rights, students in this course have the right to submit in English or in French any written work that is to be graded.
In the event of extraordinary circumstances beyond the University's control, the content and/or evaluation scheme in this course is subject to change.
As the instructor of this course I endeavor to provide an inclusive learning environment. However, if you experience barriers to learning in this course, do not hesitate to discuss them with me and the Office for Students with Disabilities, 514-398-6009.