CS224W: Machine Learning with Graphs | 2021 | Lecture 5.3 - Collective Classification

Lecture 5.3 - Collective Classification: Belief Propagation Jure Leskovec Computer Science, PhD In this lecture, we introduce belief propagation, which is a dynamic programming approach to answering probability queries in a graph. By iteratively passing messages to neighbors, the final belief is calculated if a consensus is reached. We then show the message passing with examples and generalization to tree structure. At last, we talk about the loopy belief propagation algorithm, and its pros and cons. 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: ​