InfoCoBuild

CS224W - Machine Learning with Graphs

CS224W: Machine Learning with Graphs. Instructor: Prof. Jure Leskovec, Department of Computer Science, Stanford University. Complex data can be represented as a graph of relationships between objects. Such networks are a fundamental tool for modeling social, technological, and biological systems. This course focuses on the computational, algorithmic, and modeling challenges specific to the analysis of massive graphs. By means of studying the underlying graph structure and its features, students are introduced to machine learning techniques and data mining tools apt to reveal insights on a variety of networks. Topics include: representation learning and Graph Neural Networks; algorithms for the World Wide Web; reasoning over Knowledge Graphs; influence maximization; disease outbreak detection, social network analysis. You can find more information about this course, such as lecture slides and syllabus, here. (from Stanfordonline)

Lecture 06.1 - Introduction to Graph Neural Networks


Go to the Course Home or watch other lectures:

Lecture 01 - Introduction: Machine Learning for Graphs
Lecture 02 - Traditional Methods for ML on Graphs
Lecture 03 - Lode Embeddings
Lecture 04 - Link Analysis: PageRank
Lecture 05 - Label Propagation for Node Classification
Lecture 06 - Graph Neural Networks 1: GNN Model
Lecture 07 - Graph Neural Networks 2: Design Space
Lecture 08 - Applications of Graph Neural Networks
Lecture 09 - Theory of Graph Neural Networks
Lecture 10 - Knowledge Graph Embeddings
Lecture 11 - Reasoning over Knowledge Graphs
Lecture 12 - Frequent Subgraph Mining with GNNs
Lecture 13 - Community Structure in Networks
Lecture 14 - Traditional Generative Models for Graphs
Lecture 15 - Deep Generative Models for Graphs
Lecture 16 - Advanced Topics on GNNs
Lecture 17 - Scaling Up GNNs
Lecture 18 - GNNs in Computational Biology
Lecture 19 - GNNs for Science