gordicaleksa/pytorch-GAT
A PyTorch implementation of the Graph Attention Network (GAT) architecture from Veličković et al. with Cora and PPI dataset examples.
Not currently ranked — collecting fresh signals.
star history
This repository provides a clean implementation of Graph Attention Networks in PyTorch. GATs apply self-attention mechanisms to graph-structured data, enabling nodes to weight their neighbors’ features adaptively. The implementation includes transductive learning on the Cora dataset and inductive learning on the PPI dataset, along with visualization tools for t-SNE embeddings, attention patterns, and entropy histograms.
Frequently asked
- What is gordicaleksa/pytorch-GAT?
- A PyTorch implementation of the Graph Attention Network (GAT) architecture from Veličković et al. with Cora and PPI dataset examples.
- Is pytorch-GAT open source?
- Yes — gordicaleksa/pytorch-GAT is open source, released under the MIT license.
- What language is pytorch-GAT written in?
- gordicaleksa/pytorch-GAT is primarily written in Jupyter Notebook.
- How popular is pytorch-GAT?
- gordicaleksa/pytorch-GAT has 2.7k stars on GitHub.
- Where can I find pytorch-GAT?
- gordicaleksa/pytorch-GAT is on GitHub at https://github.com/gordicaleksa/pytorch-GAT.