0
(
ratings
)
1
students
Created by:
Last updated:
Duration:
This course includes:
Unlimited Duration
Badge on Completion
Certificate of completion
Unlimited Duration
Description
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)
Course Curriculum
- Lecture 01.1 – Why Graphs Unlimited
- Lecture 01.2 – Applications of Graph ML Unlimited
- Lecture 01.3 – Choice Graph Representation Unlimited
- Lecture 02.1 – Traditional Feature-based Methods: Node Unlimited
- Lecture 02.2 – Traditional Feature-based Methods: Link Unlimited
- Lecture 02.3 – Traditional Feature-based Methods: Graph Unlimited
- Lecture 03.1 – Node Embeddings Unlimited
- Lecture 03.2 – Random Walk Approaches for Node Embeddings Unlimited
- Lecture 03.3 – Embedding Entire Graphs Unlimited
- Lecture 04.1 – PageRank Unlimited
- Lecture 04.2 – PageRank: How to Solve? Unlimited
- Lecture 04.3 – Random Walk with Restarts Unlimited
- Lecture 04.4 – Matrix Factorization and Node Embeddings Unlimited
- Lecture 05.1 – Message Passing and Node Classification Unlimited
- Lecture 05.2 – Relational and Iterative Classification Unlimited
- Lecture 05.3 – Collective Classification Unlimited
- Lecture 06.1 – Introduction to Graph Neural Networks Unlimited
- Lecture 06.2 – Basics of Deep Learning Unlimited
- Lecture 06.3 – Deep Learning for Graphs Unlimited
- Lecture 07.1 – A General Perspective on GNNs Unlimited
- Lecture 07.2 – A Single Layer of a GNN Unlimited
- Lecture 07.3 – Stacking Layer of a GNN Unlimited
- Lecture 08.1 – Graph Augmentation for GNNs Unlimited
- Lecture 08.2 – Training Graph Neural Networks Unlimited
- Lecture 08.3 – Setting Up GNN Prediction Tasks Unlimited
- Lecture 09.1 – How Expressive are Graph Neural Networks Unlimited
- Lecture 09.2 – Designing the Most Powerful GNNs Unlimited
- Lecture 10.1 – Heterogeneous and Knowledge Graph Embedding Unlimited
- Lecture 10.2 – Knowledge Graph Completion Unlimited
- Lecture 10.3 – Knowledge Graph Completion Algorithms Unlimited
- Lecture 11.1 – Reasoning in Knowledge Graphs Unlimited
- Lecture 11.2 – Answering Predictive Queries Unlimited
- Lecture 11.3 – Query2Box: Reasoning over KGs Unlimited
- Lecture 12.1 – Fast Neural Subgraph Matching and Counting Unlimited
- Lecture 12.2 – Neural Subgraph Matching Unlimited
- Lecture 12.3 – Finding Frequent Subgraphs Unlimited
- Lecture 13.1 – Community Detection in Networks Unlimited
- Lecture 13.2 – Network Communities Unlimited
- Lecture 13.3 – Louvain Algorithm Unlimited
- Lecture 13.4 – Detecting Overlapping Communities Unlimited
- Lecture 14.1 – Generative Models for Graphs Unlimited
- Lecture 14.2 – Erdos Renyi Random Graphs Unlimited
- Lecture 14.3 – The Small World Model Unlimited
- Lecture 14.4 – Kronecker Graph Model Unlimited
- Lecture 15.1 – Deep Generative Models for Graphs Unlimited
- Lecture 15.2 – Graph RNN: Generating Realistic Graphs Unlimited
- Lecture 15.3 – Scaling Up and Evaluating Graph Gen Unlimited
- Lecture 15.4 – Applications of Deep Graph Generation Unlimited
- Lecture 16.1 – Limitations of Graph Neural Networks Unlimited
- Lecture 16.2 – Position-Aware Graph Neural Networks Unlimited
- Lecture 16.3 – Identity-Aware Graph Neural Networks Unlimited
- Lecture 16.4 – Robustness of Graph Neural Networks Unlimited
- Lecture 17.1 – Scaling Up Graph Neural Networks Unlimited
- Lecture 17.2 – GraphSAGE Neighbor Sampling Unlimited
- Lecture 17.3 – Cluster GCN: Scaling UP GNNs Unlimited
- Lecture 17.4 – Scaling UP by Simplifying GNNs Unlimited
- Lecture 18 – GNNs in Computational Biology Unlimited
- Lecture 19.1 – Pre-Training Graph Neural Networks Unlimited
- Lecture 19.2 – Hyperbolic Graph Embeddings Unlimited
- Lecture 19.3 – Design Space of Graph Neural Networks Unlimited
About the instructor
Instructor Rating
Reviews
Courses
Students
