yolandalalala/GNNInterpreter
[ICLR 2023] Official implementation of the paper "GNNInterpreter"
This project helps machine learning researchers and scientists understand why a Graph Neural Network (GNN) makes specific predictions. It takes a trained GNN model and graph datasets as input, then generates visual graph patterns that highlight the key features the GNN focuses on for its decisions. This tool is for anyone who needs to ensure their GNN models are reliable and transparent, especially in fields where wrong predictions could have serious consequences.
No commits in the last 6 months.
Use this if you need to understand the underlying logic of your Graph Neural Network's predictions and identify the graph patterns it prioritizes.
Not ideal if you are looking for explanations for individual node or edge predictions, rather than the overall model's decision-making process.
Stars
16
Forks
2
Language
Jupyter Notebook
License
MIT
Last pushed
Apr 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yolandalalala/GNNInterpreter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...