weihua916/powerful-gnns
PyTorch implementation of Graph Isomorphism Networks (GIN), exploring the theoretical power of Graph Neural Networks for graph classification tasks.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of experiments from the ICLR 2019 paper ‘How Powerful are Graph Neural Networks?’ by Xu et al. It implements the GIN (Graph Isomorphism Network) algorithm, a provably expressive GNN architecture, along with baseline GNN variants for comparison. The code supports graph-level classification tasks on datasets like TU-Molecule, COLLAB, and IMDB, using node features augmented with degree information.
Frequently asked
- What is weihua916/powerful-gnns?
- PyTorch implementation of Graph Isomorphism Networks (GIN), exploring the theoretical power of Graph Neural Networks for graph classification tasks.
- Is powerful-gnns open source?
- Yes — weihua916/powerful-gnns is open source, released under the MIT license.
- What language is powerful-gnns written in?
- weihua916/powerful-gnns is primarily written in Python.
- How popular is powerful-gnns?
- weihua916/powerful-gnns has 1.3k stars on GitHub.
- Where can I find powerful-gnns?
- weihua916/powerful-gnns is on GitHub at https://github.com/weihua916/powerful-gnns.