This device is not compatible.
PROJECT
Link-Based Classification Using Graph Neural Networks
In this project, we'll create a Graph Neural Network (GNN) using the PyTorch Geometric framework, and we'll use it to classify the scientific publications of the Cora dataset.
You will learn to:
Plot data using dedicated Python libraries.
Understand the fundamentals of graph neural networks.
Get hands-on experience with the PyTorch Geometric framework.
Solve a classification problem using graph neural networks.
Skills
Deep Learning
Data Plotting
Graph Neural Networks
Prerequisites
Basic understanding of deep learning models
Hands-on experience with Python
Technologies
PyG
Python
PyTorch
Matplotlib
Project Description
Graph neural networks (GNNs) are a class of deep learning models that capture intrinsic data patterns to facilitate model training. They are finding extensive applications in social and ego networks, molecular discovery, and other domains where the data has an underlying graph structure.
In this project, we will develop a graph convolutional network (GCN) to classify the scientific publications in the Cora dataset. As the Cora dataset consists of interlinked data, using GNNs will allow us to capture more data correlations as compared to conventional neural networks for improved model performance. We will import the Cora dataset, implement the graph convolutional network, and use it to classify the scientific publications in the Cora dataset. Moreover, we will analyze the model performance for different split ratios of the dataset.
Project Tasks
1
Getting Started
Task 0: Introduction
Task 1: Import Libraries
Task 2: Load the Dataset
2
Create a Graph Neural Network
Task 3: Initialize the Graph Neural Network
Task 4: Create a forward() Function
3
Define Training and Evaluation Functions
Task 5: Define the Training Function
Task 6: Define the Evaluation Function
Task 7: Modularize the Training Process
4
Classify the Graph Nodes
Task 8: Train the GCN Model
Task 9: Plot the Results
Task 10: Evaluate the Model for Different Split Ratios
Congratulations!