Dive into a comprehensive video tutorial on Graph Neural Networks (GNNs), offering a gentle introduction to this powerful machine learning technique. Explore the fundamentals of graphs, their importance in various applications, and common graph-related tasks. Learn about graph representation and the inner workings of GNNs, including information propagation and key properties such as permutation invariance and equivariance. Discover the message passing computation process and examine different GNN variants, including convolution and attention-based approaches. Gain valuable insights into this cutting-edge field of machine learning through clear explanations and visual aids.
Graph Neural Networks- A Gentle Introduction
Overview
Syllabus
Introduction
Why graphs
What is a graph
Common graph tasks
Representation of a graph
- How does a GNN work?
- Understanding information propagation
- Key property: Permutation Invariance
- Key property: Permutation Equivariance
- Message passing computation
- GNN Variant: Convolution
- GNN Variant: Attention
- Ending
Taught by
Aladdin Persson
Related Courses
-
Graph Neural Networks Implementation in Python
-
Theory of Graph Neural Networks: Representation and Learning
-
The Sensory Neuron as a Transformer - Permutation-Invariant Neural Networks for Reinforcement Learning - Paper Explained
-
Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning
-
Building Recommendation Systems Using Graph Neural Networks
-
Graph Mining Hamilton
