benedekrozemberczki/CapsGNN
A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).
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.
Stars
1,280
Forks
198
Language
Python
License
GPL-3.0
Category
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.
Compare
Higher-rated alternatives
siapy/siapy-lib
🥷 A Python package for efficient processing of spectral images
yueliu1999/Awesome-Deep-Graph-Clustering
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods...
Tony607/Keras_Deep_Clustering
How to do Unsupervised Clustering with Keras
bourdakos1/CapsNet-Visualization
🎆 A visualization of the CapsNet layers to better understand how it works
loretoparisi/CapsNet
CapsNet (Capsules Net) in Geoffrey E Hinton paper "Dynamic Routing Between Capsules" - State Of the Art