Tiiiger/SGC
official implementation for the paper "Simplifying Graph Convolutional Networks"
This project helps classify items within a network, such as categorizing research papers in a citation network or users in a social network. You provide a dataset describing connected items and their features, and it outputs predictions for each item's category. This is useful for researchers, social scientists, or anyone working with interconnected data who needs fast and accurate classification.
848 stars. No commits in the last 6 months.
Use this if you need to quickly and accurately classify nodes in large graph-structured data, such as documents in a citation network or users in a social network.
Not ideal if your primary goal is to learn complex, non-linear relationships within your graph, as this model simplifies the network structure for speed.
Stars
848
Forks
145
Language
Python
License
MIT
Category
Last pushed
Dec 13, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tiiiger/SGC"
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.