benedekrozemberczki/CapsGNN

A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

49
/ 100
Emerging

This tool helps machine learning researchers categorize complex structures by analyzing their connections and properties. It takes descriptions of graphs (like social networks or molecular structures) with their nodes, connections, and labels as input. The output is a classification that tells you what type of graph it is. Researchers working on graph classification problems, particularly those interested in advanced neural network architectures, would use this.

1,280 stars. No commits in the last 6 months.

Use this if you need to classify entire graphs based on their structural and nodal properties, especially when existing graph neural networks struggle to capture intricate, high-level features.

Not ideal if your task is focused on classifying individual nodes within a graph or predicting links between nodes rather than the overall graph type.

graph-classification network-analysis computational-chemistry social-network-analysis bioinformatics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,280

Forks

198

Language

Python

License

GPL-3.0

Last pushed

Mar 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/benedekrozemberczki/CapsGNN"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.