tkipf/pygcn
A PyTorch reimplementation of Kipf & Welling's Graph Convolutional Networks for semi-supervised classification on graph-structured data.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of Graph Convolutional Networks (GCNs), a deep learning approach for semi-supervised learning on graph-structured data. The implementation follows the architecture described in the landmark 2016 paper by Kipf and Welling, enabling node-level classification tasks by leveraging graph structure through message passing over adjacency matrices. It uses the Cora citation network dataset for demonstration.
Frequently asked
- What is tkipf/pygcn?
- A PyTorch reimplementation of Kipf & Welling's Graph Convolutional Networks for semi-supervised classification on graph-structured data.
- Is pygcn open source?
- Yes — tkipf/pygcn is open source, released under the MIT license.
- What language is pygcn written in?
- tkipf/pygcn is primarily written in Python.
- How popular is pygcn?
- tkipf/pygcn has 5.4k stars on GitHub.
- Where can I find pygcn?
- tkipf/pygcn is on GitHub at https://github.com/tkipf/pygcn.