CS224W: Machine Learning with Graphs | 2021 | Lecture 6.1 - Graph Neural Networks Introduction

Jure Leskovec Computer Science, PhD Previously we talked about some node embedding techniques that could learn task-independent features through the process of random walks. Starting from this lecture, we introduce the exciting technique of graph neural networks, that encodes node features with multiple layers of non-linear transformations based on graph structure. Graph neural networks have shown extraordinary performance in various tasks, and could tame the complex nature of graphs. To follow along with the course schedule and syllabus, visit: To get the latest news on Stanford’s upcoming professional programs in Artificial Intelligence, visit: To view all online courses and programs offered by Stanford, visit: ​