CS224W: Machine Learning with Graphs | 2021 | Lecture 2.2 - Traditional Feature-based Methods: Link

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: Traditional Feature-based Methods: Link-level features Jure Leskovec Computer Science, PhD In this video we introduce the important task of link prediction , as well as how to extract link-level features to better tackle such type of problems. This is useful in scenarios where we need to predict missing edges, or predict edges that will appear in the future. Link level features we’ll be talking about include distance-based ones, as well as local and global neighborhood overlap. To follow along with the course schedule and syllabus, visit: