Dive into the world of Graph Neural Networks (GNNs) with this comprehensive tutorial, the first in a two-part series. Explore the fundamentals of graphs, their mathematical representations, and practical applications using Python libraries like NetworkX and PyG (PyTorch Geometric). Learn how to visualize and manipulate graph data, understand the relationship between GNNs and Convolutional Neural Networks (CNNs), and gain insights into various graph representations. Cover topics such as graph basics, NetworkX programming, GNN introduction, and PyG fundamentals. By the end of this tutorial, acquire the technical knowledge needed to code GNNs and apply them to real-world problems, setting the stage for more advanced concepts in part two of the series.
Overview
Syllabus
- Tutorial Introduction
- Part 1 Tutorial Content
- Part 2 Tutorial Content
- Resources & Acknowledgement
- Graph Data Use Cases
- Fundamentals of Graph
- Mathematics of Graph
- Coding Graph with NetworkX Library
- Neighbors in Graph
- Path_graph Type
- Directed Graph
- Adjacency Matrix
- MultiDirected Graph
- MultiEdge Attributes
- MultiGraph
- Sudoku Graph
- Grid Graph
- Graph Neural Networks GNN
- GNN + CNN = GCN
- PyG Introduction
- What is a Tensor?
- Datasets in PyG
- Graph View in yEd
- Create Graph in PyG
- Recap
Taught by
Prodramp
Related Courses
-
Graph Neural Networks Implementation in Python
-
Mastering Neural Networks and Model Regularization
-
Graph Neural Networks for Information Extraction with PyTorch
-
Link Prediction with Graph Neural Networks Using DGL and PyG
-
Graph Attention Networks - GNN Paper Explained
-
Graph Neural Networks- A Gentle Introduction
4.0
