sigeisler/s2gnn
Spatio-Spectral Graph Neural Networks (S²GNN)
This project helps machine learning engineers and researchers analyze complex relationships in data that can be represented as graphs, such as molecular structures or social networks. It takes graph-structured data and applies a specialized neural network to identify patterns and make predictions, outputting insights like classifications or property predictions. The primary users are those working on advanced machine learning models for graph data.
No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer developing and experimenting with cutting-edge graph neural network architectures for complex graph data.
Not ideal if you need a plug-and-play solution for basic graph analysis or do not have experience with advanced machine learning model development.
Stars
19
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sigeisler/s2gnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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.