Home

Welcome to MUPPET-XAI documentation!

Multiple Perturbation eXplainable Artificial Intelligence (MUPPET-XAI) is a multimodal python library for explaining and interpreting Pytorch models through perturbation-based XAI methods. It supports all data modalities (including images, tabular data, time series, ...).

Principle

Given a black-box model \(f\) that only provides inference functionality, regardless of its inner working, and a data point \(x\). The goal is to understand the prediction \(f(x)\) made by the model by perturbing the input data feature values \(x'\) and observing the model \(f\) prediction on those perturbations.

The perturbation-based methods follow four steps:

1. Generate the masks to use for perturbing the input data \(x\),

2. Apply those masks on the input data to get the \(x'\),

3. Calculate feature scores/attributions of every perturbation from the model prediction on perturbed data \(f(x')\) and on original data,

4. Finally aggregate the attributions to find the final local explanation such as feature importance, heat-maps, ...

This documentation is complementary to the README.md in the MUPPET-XAI repository and provides documentation for how to install MUPPET-XAI, how to contribute and details on the API.

MUPPET-XAI can be installed from PyPI:

pip install muppet-xai

Contents

Installation

• Quick installation

Getting Started

• Getting Started
• Benchmarking

API Reference

• muppet package

Developer Documentation

• Contribute to MUPPET-XAI

Citation

If you find this toolkit or its companion paper Muppet: A Modular and Constructive Decomposition for Perturbation-Based Explanation Methods interesting or useful in your research, please use the following Bibtex annotation to cite us:

@inproceedings{ferre2025muppet,
  title={Muppet: A Modular and Constructive Decomposition for Perturbation-Based Explanation Methods},
  author={Ferré, Quentin and Bachchar, Ismail and Arroubat, Hakima and Jedidi, Aziz and Achenchabe, Youssef and Bonnefoy, Antoine},
  booktitle={2025 International Joint Conference on Neural Networks (IJCNN)},
  pages={1--8},
  year={2025},
  organization={IEEE}
}