aimclub/StableGNN
Framework for autonomous learning of explainable graph neural networks
This tool helps researchers and data scientists analyze complex network data, such as social connections or biological pathways. You provide your graph data, including connections (edges), node labels, and optional node attributes. It then processes this information to deliver explainable predictions about individual nodes or entire graphs, helping you understand the underlying patterns and relationships within your data.
No commits in the last 6 months.
Use this if you need to make sense of interconnected data, classify nodes or graphs, and understand why your graph neural network model is making specific predictions.
Not ideal if your data is not structured as a graph, or if you primarily need to generate new graph structures without focusing on classification or explanation.
Stars
33
Forks
7
Language
Jupyter Notebook
License
BSD-3-Clause
Last pushed
Feb 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aimclub/StableGNN"
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...