danielegrattarola/keras-gat
Keras implementation of Graph Attention Networks for semi-supervised node classification on graph data.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow/Keras implementation of the Graph Attention Network (GAT) model from the 2018 ICLR paper by Veličković et al. The model uses attention mechanisms to aggregate features from neighboring nodes in a graph, enabling semi-supervised learning on graph-structured data. The implementation includes utilities for data loading and splitting, and was designed to work with citation datasets like Cora.
Frequently asked
- What is danielegrattarola/keras-gat?
- Keras implementation of Graph Attention Networks for semi-supervised node classification on graph data.
- Is keras-gat open source?
- Yes — danielegrattarola/keras-gat is open source, released under the MIT license.
- What language is keras-gat written in?
- danielegrattarola/keras-gat is primarily written in Python.
- How popular is keras-gat?
- danielegrattarola/keras-gat has 493 stars on GitHub.
- Where can I find keras-gat?
- danielegrattarola/keras-gat is on GitHub at https://github.com/danielegrattarola/keras-gat.