danielegrattarola/spektral
Graph Neural Networks with Keras and Tensorflow 2.
This helps data scientists and machine learning engineers who work with interconnected data. It takes in data represented as graphs (like social networks, molecular structures, or connected devices) and helps build machine learning models to classify nodes, predict properties, or find hidden relationships within those graphs. The output is a trained model ready to make predictions or generate insights on new graph data.
2,395 stars. Used by 1 other package. No commits in the last 6 months. Available on PyPI.
Use this if you need to build deep learning models for data where the relationships between items are as important as the items themselves, such as in social networks, chemical compounds, or recommender systems.
Not ideal if your data is best represented in traditional tables, images, or plain text, without inherent graph structures.
Stars
2,395
Forks
341
Language
Python
License
MIT
Category
Last pushed
Jan 21, 2024
Commits (30d)
0
Dependencies
11
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danielegrattarola/spektral"
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.