Keras Implementation of Graph Attention Networks for Node Classification 🕸
This repo contains the model and the notebook to this Keras example on Graph Attention Networks for Node Classification.
Full credits to: Alexander Kensert
Background Information
Graph neural networks is the preferred neural network architecture for processing data structured as graphs (for example, social networks or molecule structures), yielding better results than fully-connected networks or convolutional networks.
This tutorial implements a specific graph neural network known as a Graph Attention Network (GAT) to predict labels of scientific papers based on the papers they cite (using the Cora dataset).
References For more information on GAT, see the original paper Graph Attention Networks as well as DGL's Graph Attention Networks documentation.
- Downloads last month
- 17
Unable to determine this model’s pipeline type. Check the
docs
.