gordicaleksa/pytorch-GAT
My implementation of the original GAT paper (Veličković et al.). I've additionally included the playground.py file for visualizing the Cora dataset, GAT embeddings, an attention mechanism, and entropy histograms. I've supported both Cora (transductive) and PPI (inductive) examples!
This project helps you understand and experiment with Graph Attention Networks (GATs) for tasks like classifying research papers based on citations or predicting protein interactions. It takes graph data, where connections between items are important, and outputs visualizations of how the network 'pays attention' to different connections and how it groups similar items together. This is for machine learning practitioners, researchers, and students interested in graph neural networks.
2,655 stars. No commits in the last 6 months.
Use this if you want to learn about and visualize how Graph Attention Networks process information on graph-structured data like citation networks (Cora) or protein-protein interaction networks (PPI).
Not ideal if you need a production-ready, highly optimized GAT implementation for a complex, large-scale application.
Stars
2,655
Forks
352
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gordicaleksa/pytorch-GAT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.