Learning Graph Neural Networks

Learn about the use cases of graph modeling and find out how to train graph neural networks and evaluate its results.

Introduction

• Introducing graph neural networks
• Prerequisites

1. Understanding Graphs

• Undirected and directed graphs
• Other graph types
• Graph representations

2. Introducing Graph Machine Learning

• Prediction tasks with graphs
• Approaches to graph machine learning
• Challenges of using graphs in machine learning

3. Introducing Graph Neural Networks

• Graph neural networks intuition
• Understanding the structure of GNNs
• The graph neural network architecture
• Message passing transformation and aggregation
• Training a GNN

4. Representing Graphs in PyTorch Geometric

• Introducing PyTorch Geometric
• Exercise: Set up the Colab environment and libraries
• Exercise: Setting up a graph data structure in PyG
• Exercise: Visualizing graphs and exploring graph methods
• Exercise: Visualizing and exploring a directed graph
• Exercise: Exploring the cora dataset
• Exercise: Mini batches of data
• Exercise: Representing heterogeneous graphs in PyG

5. Performing Node Classification Using GNNs

• Exercise: The CiteSeer dataset for node classification
• Exercise: Setting up a DNN as a baseline model
• Exercise: Training the baseline model
• Exercise: Setting up a graph convolutional network
• Exercise: Training a GCN

Conclusion

• Summary and next steps