Framework allowing users to easily set up, execute and visualize counterfactual explanation experiments on ML models.
-
Updated
Jun 22, 2022 - Jupyter Notebook
Framework allowing users to easily set up, execute and visualize counterfactual explanation experiments on ML models.
This is the repository code for IFC1 - A novel algorithm to generate algorithmic recourse keeping in mind user preference
Python implementation of the work "The importance of Time in Causal Algorithmic Recourse"
Repository for "Endogenous Macrodynamics in Algorithmic Recourse" (Altmeyer et al., 2023)
Code for the paper "Personalized Algorithmic Recourse with Preference Elicitation"
Recourse Explanation Library in JAX
Robust Bayesian Recourse: a robust model-agnostic algorithmic recourse method (UAI'22)
Robust Bayesian Recourse: a robust model-agnostic algorithmic recourse method (UAI'22)
(Explainable) Algorithmic Recourse with Reinforcement Learning and MCTS (FARE and E-FARE)
CFXplorer generates optimal distance counterfactual explanations for a given machine learning model.
A Julia package for modelling Algorithmic Recourse Dynamics.
Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis.
Counterfactual Shapley Additive Explanation: Experiments
RootCLAM: On Root Cause Localization and Anomaly Mitigation through Causal Inference (CIKM 2023)
Counterfactual SHAP: a framework for counterfactual feature importance
Code and data for decision making under strategic behavior, NeurIPS 2020 & Management Science 2024.
Code to reproduce our paper on probabilistic algorithmic recourse: https://arxiv.org/abs/2006.06831
Add a description, image, and links to the algorithmic-recourse topic page so that developers can more easily learn about it.
To associate your repository with the algorithmic-recourse topic, visit your repo's landing page and select "manage topics."