Skip to content
Caspian88 edited this page Jun 28, 2024 · 1 revision

Welcome to the Node-Classification-with-Graph-Neural-Networks-FNN

Introduction Many datasets in various machine learning (ML) applications have structural relationships between their entities, which can be represented as graphs. Such application includes social and communication networks analysis, traffic prediction, and fraud detection. Graph representation Learning aims to build and train models for graph datasets to be used for a variety of ML tasks.

This example demonstrate a simple implementation of a Graph Neural Network (GNN) model. The model is used for a node prediction task on the Cora dataset to predict the subject of a paper given its words and citations network.

Note that, we implement a Graph Convolution Layer from scratch to provide better understanding of how they work. However, there is a number of specialized TensorFlow-based libraries that provide rich GNN APIs, such as Spectral, StellarGraph, and GraphNets.

Clone this wiki locally