gasteigerjo/ppnp
PPNP & APPNP models from "Predict then Propagate: Graph Neural Networks meet Personalized PageRank" (ICLR 2019)
This project helps machine learning researchers and practitioners accurately classify nodes within complex network data, such as citation networks or social graphs. It takes a graph dataset with nodes and their connections (like papers and their citations) and outputs improved classifications for each node. Researchers working on graph machine learning tasks, especially those in academia or data science roles, would find this useful.
323 stars. No commits in the last 6 months.
Use this if you need to implement or experiment with specific advanced graph neural network models (PPNP and APPNP) for node classification tasks.
Not ideal if you are looking for a simple, off-the-shelf solution for general graph analysis or visualization without deep involvement in model architecture.
Stars
323
Forks
55
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gasteigerjo/ppnp"
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.