JonathanCrabbe

Jonathan Crabbé's repositories

Dynamask

This repository contains the implementation of Dynamask, a method to identify the features that are salient for a model to issue its prediction when the data is represented in terms of time series. For more details on the theoretical side, please read our ICML 2021 paper: 'Explaining Time Series Predictions with Dynamic Masks'.

Language:PythonMIT69 2 10

Label-Free-XAI

This repository contains the implementation of Label-Free XAI, a new framework to adapt explanation methods to unsupervised models. For more details, please read our ICML 2022 paper: 'Label-Free Explainability for Unsupervised Models'.

Language:PythonMIT22 10

Simplex

This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.

Language:PythonApache-2.022 3 2

FourierDiffusion

This repository implements time series diffusion in the frequency domain.

Language:Jupyter NotebookMIT1500

Symbolic-Pursuit

Github for the NIPS 2020 paper "Learning outside the black-box: at the pursuit of interpretable models"

Language:Jupyter Notebook14 4 1

CARs

This repository contains the implementation of Concept Activation Regions, a new framework to explain deep neural networks with human concepts. For more details, please read our NeurIPS 2022 paper: 'Concept Activation Regions: a Generalized Framework for Concept-Based Explanations.

Language:PythonApache-2.09 20

RobustXAI

This repository contains the implementation of the explanation invariance and equivariance metrics, a framework to evaluate the robustness of interpretability methods.

Language:Jupyter Notebook8 20

ITErpretability

This repository contains the implementation of ITErpretability, a new framework to benchmark treatment effect deep neural network estimators with interpretability. For more details, please read our NeurIPS 2022 paper: 'Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability'.

Language:Jupyter NotebookBSD-3-Clause2 40