TWS - ML, NN, and GNN using PyTorch and PyG – Part 2: GNN and PyG (2nd Offering)

This workshop provides an overview of a significant framework in deep learning: PyTorch (and PyTorch Geometric). The second session introduces PyTorch Geometric (PyG), focusing on the application of graph neural networks in analyzing complex graph data. Participants will engage with practical examples and theoretical discussions, enhancing their understanding of these frameworks' roles in graph neural networks and deep learning research. This workshop is aimed at researchers and students seeking to deepen their knowledge of graph neural networks.

 

• Introduction to Graph Neural Networks (GNNs); Exploring the basics of GNNs.

• Graph Theory Fundamentals; Understanding graphs, nodes, edges.

• PyTorch Geometric Overview; Focusing on its role in simplifying GNN development.

• Data Handling in PyTorch Geometric; Techniques for loading, processing, and utilizing graph data.

• Building GNN Models; Constructing GNN models.

• Training GNNs; Loss function selection, backpropagation, and optimization strategies.

• Hands-on Experience; Implement a GNN model to tackle a real-world problem.

 

• Basic programming experience in Python.

• Understanding of fundamental machine learning concepts.

• Familiarity with the core principles of graph neural networks is helpful but not mandatory.

 

Soroush is a Ph.D. student and research assistant at the School of Computer Science. His main research area is Natural Language Processing and Information Retrieval on social networks.