This course was designed to get you up to speed with Graph Neural Networks so that you can both understand seminal papers in the field and implement GNNs using modern software tools. If you're wanting to understand models like Graph Convolutional Networks and Graph Attention Networks (i.e., "deep learning on graphs"), this course will help you get there. It was constructed around three elements:
- Theory, to familiarize you with the foundational topics quickly and efficiently (i.e., not more complicated than it needs to be)
- Practice, to walk you thru Hands-On examples that span the major applications of Node Classification, Link Prediction and Graph Classification and discuss practical engineering problems. This section runs with cohorts of students and therefore enrollment is limited.
- Community, to get you engaged with fellow students in the form of group discussion and code reviews. Since this works best with a cohort of students, it will be wrapped into the "Hands-On" section.
The Theory section consists of self-paced videos, quizzes and a curated set of references designed to efficiently teach you the core mathematical concepts that underpin the foundations of GNNs. This section is self-directed and fully available at the time of enrollment.
The Hands-on section is a synchronous experience over a 6-week period in which a cohort of students work on the same material and help one another through e.g., code reviews. The content consists of model-building code exercises, screencasts that walk you through the solutions, and an additional set of lecture-style videos that frame the ML tasks and discuss practical problems of building GNNs, like scalability and over-smoothing. See the FAQ below for the Hands-On course schedule.
It's expected that students of this course participate in community activities, such as discussions in chat and peer-to-peer code reviews. All participants will receive access to a course GitHub organization where course and student code will be hosted, and a private Discord room where Zak and students will discuss course material and engage with the community.
This course assumes basic familiarity with GitHub and building ML models in PyTorch. Please see the component course pages for additional details.
In addition to this core content, there is also a set of bonus videos that discuss cutting edge GNN research and applications with the original authors. For example, we dive into work from Deep Mind with Jonathan Godwin on how they used GNNs to model complex physics simulators, and discuss industry applications with scientists from Twitter and Uber.
Note: the Hands-On material will be released starting on April 21, 2023. Upon enrollment you will have immediate access to the Theory content shown below. See the FAQ for the detailed course schedule.
Frequently Asked Questions
What is the schedule for the Hands-on section of the course?
The Hands-On start date is April 21st, 2023 and will run for six weeks until June 4th, 2023. Enrollment will remain open until this start date, and the Theory material will be available immediately upon enrollment. The Hands-On course material will begin being released on the start date and new content will be released each week. Specifically, there are 3 sub-sections (Node Classification, Link Prediction and Graph Classification), each of which lasts 2 weeks and contains an exercise, a solution video and lecture content on applied topics.
Do I still have access to the material after the 6 weeks?
Yes. At the end of the course, you will be auto-enrolled into a permanent clone of this course that will give you indefinite access to the materials.
Can I get a refund if I'm unhappy with my purchase?
All purchases have a 30-day money back guarantee.
GNNs as the "Next Big Thing"
The topic of Graph Representation Learning has been exploding in popularity, but it's still relatively early days. Between 10-20% of all papers published at top conferences were on the topic of ML on graphs. Despite this popularity in the research community, these methods are just beginning to gain traction in industry as the toolsets mature (e.g., DeepMind with Travel time estimation in Google Maps). For those looking to be at the bleeding edge, this is a wonderful time to jump in.
Hi, I'm Zak
I am an Applied Scientist in FAANG that specializes in building systems supporting GNNs in industry. I also run the WelcomeAIOverlords YouTube channel, a Discord community and blog. This course uses the same approach of explaining things simply, but will go much deeper into the theory and applications of GNNs.