Generate Diverse Counterfactual Explanations for any machine learning model.
-
Updated
Apr 17, 2024 - Python
Generate Diverse Counterfactual Explanations for any machine learning model.
Optimal binning: monotonic binning with constraints. Support batch & stream optimal binning. Scorecard modelling and counterfactual explanations.
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
An Open-Source Library for the interpretability of time series classifiers
Model Agnostic Counterfactual Explanations
The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era computer vision solutions.
Meaningfully debugging model mistakes with conceptual counterfactual explanations. ICML 2022
A collection of algorithms of counterfactual explanations.
CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox
This repository contains the official code for the CVPR 2023 paper ``Adversarial Counterfactual Visual Explanations''
Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"
Code to reproduce our paper on probabilistic algorithmic recourse: https://arxiv.org/abs/2006.06831
Code accompanying the paper "Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers"
Official Code for the ACCV 2022 paper Diffusion Models for Counterfactual Explanations
Molecular Explanation Generator
Global Counterfactual Explainer for Graph Neural Networks
Counterfactual Explanation Based on Gradual Construction for Deep Networks Pytorch
Local Universal Rule-based Explanations
Easiest way to generate counterfactual explanations
Text-to-Image Models for Counterfactual Explanations: a black-box approach Official Code. WACV 2024
Add a description, image, and links to the counterfactual-explanations topic page so that developers can more easily learn about it.
To associate your repository with the counterfactual-explanations topic, visit your repo's landing page and select "manage topics."