CS224W: Machine Learning with Graphs | 2021 | Lecture 19.1 - Pre Training Graph Neural Networks

Jure Leskovec Computer Science, PhD There are two challenges in applying GNNs to scientific domains: scarcity of labeled data and out-of-distribution prediction. In this video we discuss methods for pre-training GNNs to resolve these challenges. The key idea is to pre-train both node and graph embeddings, which leads to significant performance gains on downstream tasks. More details can be found in the paper: Strategies for Pre-training Graph Neural Networks: 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: