realMoana/ProxyExplainer
ProxyExplainer for Graph Neural Networks
This tool helps machine learning engineers and researchers understand why their Graph Neural Networks (GNNs) make certain predictions on molecular or social network data. It takes your trained GNN model and a graph as input, then generates simpler, 'proxy' graphs that show the most influential parts of the original graph in driving the GNN's decision. This helps you interpret complex GNN behavior for tasks like drug discovery or social network analysis.
No commits in the last 6 months.
Use this if you need to explain the predictions of your Graph Neural Network models by identifying which specific parts of a graph are most important to its output.
Not ideal if you are working with non-graph structured data or if you need an explainer that operates differently from generating simplified, in-distribution proxy graphs.
Stars
15
Forks
2
Language
Python
License
—
Last pushed
Oct 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/realMoana/ProxyExplainer"
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...