danielegrattarola/keras-gat
Keras implementation of the graph attention networks (GAT) by Veličković et al. (2017; https://arxiv.org/abs/1710.10903)
This is a Keras implementation of a Graph Attention Network (GAT) for researchers and practitioners working with graph-structured data. It takes a graph as input and processes it to generate node-level predictions, such as classifying scientific papers based on their citation network. This is for machine learning researchers and data scientists exploring early graph neural network architectures.
494 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or data scientist specifically looking to experiment with the original Keras implementation of the Graph Attention Network (GAT) paper.
Not ideal if you need a actively maintained, modern Keras/TensorFlow implementation of GAT, as this project is deprecated and may not work with current software versions.
Stars
494
Forks
127
Language
Python
License
MIT
Category
Last pushed
Oct 26, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielegrattarola/keras-gat"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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.