aiim-research/GRETEL
GRETEL is a framework for the development and evaluation of Counterfactual Explanation methods for Graph Classifiers
This framework helps researchers quickly develop and test new methods for explaining decisions made by graph-based machine learning models. It takes various datasets and different explanation techniques as input, providing a standardized way to evaluate how well these explanations work. Researchers in machine learning who are focused on making complex graph models more understandable, especially in fields like health and finance, would use this.
Use this if you are a researcher designing and evaluating techniques to explain why a graph-based AI made a particular decision.
Not ideal if you are an end-user simply looking to understand a specific model's decision without developing new explanation methods.
Stars
23
Forks
22
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/aiim-research/GRETEL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sdv-dev/SDV
Synthetic data generation for tabular data
sdv-dev/SDGym
Benchmarking synthetic data generation methods.
NVIDIA-NeMo/DataDesigner
🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch...
AlexanderVNikitin/tsgm
Generation and evaluation of synthetic time series datasets (also, augmentations,...
mostly-ai/mostlyai
Synthetic Data SDK ✨