Welcome to ReVEL’s documentation!

ReVEL(Robust Evaluation VEctorized Loca-linear-explanation) is a Python library that provides series of tools for Explinable Artificial Intelligence(XAI) from the perspective of the audition of black-box. Specifically, it provides a framework for the generation and evaluation of Local Linear Explanations(LLEs).

This library develops the framework proposed on the paper REVEL Framework to Measure Local Linear Explanations for Black-Box Models: Deep Learning Image Classification Case Study. If you use this library in your research, please cite the paper as follows:

@article{sevillano2023revel,
title={REVEL Framework to Measure Local Linear Explanations for Black-Box Models: Deep Learning Image Classification Case Study},
author={Sevillano-Garc{\'\i}a, Iv{\'a}n and Luengo, Juli{\'a}n and Herrera, Francisco},
journal={International Journal of Intelligent Systems},
volume={2023},
number={1},
pages={8068569},
year={2023},
publisher={Wiley Online Library}
}

Contents

• 1. Introduction
  • 1.1. Installation
  • 1.2. First example
  • 1.3. Citation
• 2. Modules
  • 2.1. Perturbations
  • 2.2. Local Linear Explanations
  • 2.3. ReVel
• 3. Examples
  • 3.1. First steps
  • 3.2. Obtaining an explanation
  • 3.3. Graphics

[LL17]

Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL: https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf.

[RSG16]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. "why should i trust you?": explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '16, 1135–1144. New York, NY, USA, 2016. Association for Computing Machinery. URL: https://doi.org/10.1145/2939672.2939778, doi:10.1145/2939672.2939778.

[VS08]

Andrea Vedaldi and Stefano Soatto. Quick shift and kernel methods for mode seeking. In European conference on computer vision, 705–718. Springer, 2008.