Basics of Graph Neural Networks
This course is a quick tour of important concepts for machine learning on graphs. It will introduce the foundational concept of message passing and explain core algorithms, like Label Propagation, Graph Convolutional Networks and Graph Attention Networks. It will also show you how to implement a Graph Convolutional Network from scratch using only NumPy. In addition to the videos, there are quizzes to test your comprehension on key concepts.
There is also a set of bonus videos that discuss cutting edge GNN research with the primary authors. For example, we dive into a work from Deep Mind with Jonathan Godwin on using GNNs to model complex physics.
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.
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. My focus is on making content that explains concepts as simply and clearly as possible.
