Gain insights into graph machine learning fundamentals. Explore graph analytics, and advanced topics like graph embedding and neural networks, enhancing your skills for practical applications.

networkx.tar.gz

Networkx

Are you ready to attain mastery in graph machine learning? Graphs are ubiquitous and have diverse applications in various fields. In this introductory course, you will learn the fundamentals of graph machine learning so that you’re able to work with different types of graphs, state-of-the-art graph machine learning techniques, and various graph analytics tasks.

The course begins with the basics of graphs and gradually progresses to more advanced topics, including graph embedding and its different techniques and different use cases built on knowledge graphs. 

By the end of the course, you will have gained hands-on experience in creating and manipulating graphs, as well as a comprehensive understanding of knowledge graphs and graph neural networks. This course will equip you with the skills and knowledge to step into advanced graph machine learning topics for research or practical applications and take your career to the next level.

Introduction to Graph Machine Learning

The `RESCAL` method is based on tensor factorization. The idea here is to express the graph as a three-way tensor so that $X ∈ R^{n×n×m}$, where $n$ is the number of entities and $m$ is the number of relations. The tensor holds value $1$, denoting the presence of a relation between the entities, and $0$ if there are none.

> **Note:** A tensor is a multidimensional array. In other words, a vector is a first-order tensor, and a matrix is a second-order tensor. If the order is greater than two, we just call it a high-order tensor or simply a tensor.

Learn about factorization-based knowledge graph embedding methods.

About the Course

Introduction to Graph Theory

Graph Embeddings

Supervised and Unsupervised Graph ML

Graph Neural Networks

Link-Based Classification Using Graph Neural Networks

Knowledge Graph

Knowledge Graph Embeddings

Case Study: Link Prediction on a Social Network Graph

Case Study: Node Classification on a Biological Graph

Appendix

Factorization-Based Methods