joisino/gnnbook
書籍『グラフニューラルネットワーク』のサポートサイトです。
This project provides Jupyter notebooks that demonstrate various Graph Neural Network (GNN) algorithms. It takes real-world data structured as graphs (like social networks or molecular structures) and applies GNN techniques to perform tasks such as node classification, graph classification, or link prediction. This resource is designed for students, researchers, and machine learning practitioners who want to understand and implement GNNs.
No commits in the last 6 months.
Use this if you are studying Graph Neural Networks and need practical, runnable examples to deepen your understanding of algorithms like Label Propagation, Graph Convolutional Networks, or Graph Attention Networks.
Not ideal if you are looking for a high-level API or a complete solution for deploying GNN models in a production environment without needing to understand the underlying implementation details.
Stars
67
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joisino/gnnbook"
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.