weihua916/powerful-gnns
How Powerful are Graph Neural Networks?
This is a tool for machine learning researchers and practitioners who are working with graph-structured data. It provides the PyTorch implementation of Graph Isomorphism Network (GIN) experiments described in the paper 'How Powerful are Graph Neural Networks?'. You can input graph datasets and train GNN models, getting out insights into model performance and the effectiveness of different GNN architectures on various graph tasks.
1,275 stars. No commits in the last 6 months.
Use this if you are a researcher or advanced practitioner experimenting with Graph Neural Networks and need to reproduce or build upon the GIN model's capabilities for graph classification.
Not ideal if you are a beginner looking for a high-level library to apply GNNs without deep understanding of their architecture, or if you need a pre-trained model for immediate inference.
Stars
1,275
Forks
226
Language
Python
License
MIT
Category
Last pushed
Jul 01, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/weihua916/powerful-gnns"
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.