mdeff/cnn_graph
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
This project offers an efficient way to apply Convolutional Neural Networks (CNNs) to data that has a natural graph structure. It takes in your data, a target you want to predict or classify, and optionally an adjacency matrix describing the connections between your data points. The output is a trained graph CNN model that can then be used for tasks like classification or prediction, which can be valuable for machine learning researchers and practitioners working with complex relational datasets.
1,369 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or practitioner working with datasets where the relationships between data points are important and can be represented as a graph, and you want to leverage the power of CNNs for tasks like classification or prediction.
Not ideal if your data is not inherently structured as a graph, or if you are looking for a plug-and-play solution without needing to understand deep learning concepts.
Stars
1,369
Forks
390
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 13, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mdeff/cnn_graph"
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.