tkipf/gae
TensorFlow implementation of Graph Auto-Encoders for unsupervised learning and link prediction on graph-structured data.
Not currently ranked — collecting fresh signals.
star history
This repository provides a TensorFlow implementation of Graph Auto-Encoders (GAEs) and Variational Graph Auto-Encoders, neural network models for unsupervised learning on graph data. The models use graph convolutional layers to learn node embeddings for tasks such as link prediction, clustering, and matrix completion. The implementation builds on Graph Convolutional Networks (GCNs) and supports citation network datasets like Cora, Citeseer, and Pubmed.
Frequently asked
- What is tkipf/gae?
- TensorFlow implementation of Graph Auto-Encoders for unsupervised learning and link prediction on graph-structured data.
- Is gae open source?
- Yes — tkipf/gae is open source, released under the MIT license.
- What language is gae written in?
- tkipf/gae is primarily written in Python.
- How popular is gae?
- tkipf/gae has 1.7k stars on GitHub.
- Where can I find gae?
- tkipf/gae is on GitHub at https://github.com/tkipf/gae.