This course provides a deep dive into the graph convolutional networks paper, covering all the details behind GCN and exploring 3 different perspectives: spectral, Weisfeiler-Lehman, and GAT. The course aims to teach students about GCN, graph Laplacian regularization methods, semi-supervised learning processes, graph embedding methods, and various GCN variations. The teaching method involves in-depth explanations, visualizations, and benchmarking. This course is intended for individuals interested in graph neural networks and deep learning concepts.
Overview
Syllabus
Intro to GCNs
Graph Laplacian regularization methods
GCN method in-depth explanation
Vectorized form explanation
Spectral methods the motivation behind GCNs
Visualizing GCN hidden features t-SNE
Explanation of semi-supervised learning process
Graph embedding methods, results
Different variations of GCN
Speed benchmarking & limitations
Weisfeiler-Lehman perspective GCN vs GIN
GAT perspective, consequences of WL
GNN depth
Taught by
Aleksa Gordić - The AI Epiphany
Related Courses
-
Graph Attention Networks - GNN Paper Explained
-
Graph SAGE - Inductive Representation Learning on Large Graphs - GNN Paper Explained
-
Graph Convolutional Network Paper Explained
-
How to Get Started With Graph ML - Blog Walkthrough
-
Graph Attention Network Project Walkthrough
-
Graph Neural Networks- A Gentle Introduction
