yramon / edc
Heuristic best-first algorithm for computing Evidence Counterfactuals (SEDC): explaining the model predictions of any classifier using a minimal set of features, such that removing these features results in a predicted class change.
☆15Updated 4 years ago
Alternatives and similar repositories for edc:
Users that are interested in edc are comparing it to the libraries listed below
- Adversarial Attacks on Post Hoc Explanation Techniques (LIME/SHAP)☆82Updated 2 years ago
- Model Agnostic Counterfactual Explanations☆87Updated 2 years ago
- Hybrid algorithm based on SEDC and LIME for computing Evidence Counterfactuals (LIME-Counterfactual): explaining the model predictions of…☆11Updated 4 years ago
- CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox☆43Updated 8 months ago
- Code repository for our paper "Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift": https://arxiv.org/abs/1810.119…☆104Updated last year
- Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University☆45Updated 2 years ago
- A lightweight implementation of removal-based explanations for ML models.☆59Updated 3 years ago
- Application of the LIME algorithm by Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin to the domain of time series classification☆95Updated last year
- LOcal Rule-based Exlanations☆53Updated last year
- Explaining Anomalies Detected by Autoencoders Using SHAP☆40Updated 3 years ago
- A toolbox for differentially private data generation☆131Updated last year
- Multi-Objective Counterfactuals☆41Updated 2 years ago
- A Natural Language Interface to Explainable Boosting Machines☆65Updated 8 months ago
- Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent…☆54Updated 6 years ago
- ☆90Updated 3 years ago
- python tools to check recourse in linear classification☆75Updated 4 years ago
- This repository provides details of the experimental code in the paper: Instance-based Counterfactual Explanations for Time Series Classi…☆18Updated 3 years ago
- A Python package for unwrapping ReLU DNNs☆69Updated last year
- Modular Python Toolbox for Fairness, Accountability and Transparency Forensics☆77Updated last year
- simple customizable risk scores in python☆136Updated last year
- Public home of pycorels, the python binding to CORELS☆77Updated 4 years ago
- Explaining Anomalies Detected by Autoencoders Using SHAP☆32Updated 5 years ago
- Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)☆40Updated 2 years ago
- Repository for code release of paper "Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Data" (AISTATS 2020)☆50Updated 5 years ago
- Rule Extraction Methods for Interactive eXplainability☆43Updated 2 years ago
- For calculating Shapley values via linear regression.☆67Updated 3 years ago
- CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms☆286Updated last year
- A TensorFlow [2.0] implementation of ProSeNet: "Interpretable and Steerable Sequence Learning via Prototypes" (Ming et al., 2019)☆12Updated 5 years ago
- Python package to compute interaction indices that extend the Shapley Value. AISTATS 2023.☆17Updated last year
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆127Updated 4 years ago