sidneyarcidiacono/UnderstandingGCNs
The code, citation & note companion to the AICamp Webinar "Understanding Graph Convolutional Networks" hosted on September 7th, 2021.
This project helps data scientists and researchers predict characteristics of interconnected data, like molecular structures or gene interactions, by leveraging Graph Convolutional Networks (GCNs). It takes graph-structured biological datasets, such as protein interaction networks, and outputs predictions based on the relationships within the data. It's designed for those working with complex, relational data where traditional deep learning methods might fall short.
No commits in the last 6 months.
Use this if you are a data scientist or researcher working with interconnected biological data and need to make predictions that consider the relationships between data points.
Not ideal if your data is not inherently structured as a graph or if you are looking for a general-purpose deep learning tutorial unrelated to graph-structured data.
Stars
11
Forks
5
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Sep 21, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sidneyarcidiacono/UnderstandingGCNs"
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.