PyXAI: An XAI Library for Tree-Based Models

Gilles Audemard; Jean-Marie Lagniez; Pierre Marquis; Nicolas Szczepanski

IJCAI 2024poster4 citations

PyXAI: An XAI Library for Tree-Based Models

Gilles Audemard, Jean-Marie Lagniez, Pierre Marquis, Nicolas Szczepanski

Abstract

PyXAI (Python eXplainable AI) is a Python library designed for providing explanations and cor- recting tree-based Machine Learning (ML) models. It is suited to decision trees, random forests, and boosted trees, when used for regression or classification tasks. In contrast to many model-agnostic approaches to XAI, PyXAI exploits the model it- self to generate explanations, ensuring them to be faithful. PyXAI includes several algorithms for the generation of explanations, which can be abductive or contrastive. PyXAI also includes algorithms for correcting tree-based models when their predictions conflict with pieces of user knowledge.

Machine Learning: ML: Explainable/Interpretable machine learningAI Ethics, Trust, Fairness: ETF: Explainability and interpretability

BibTeX

@inproceedings{ijcai2024p989,
  title     = {PyXAI: An XAI Library for Tree-Based Models},
  author    = {Audemard, Gilles and Lagniez, Jean-Marie and Marquis, Pierre and Szczepanski, Nicolas},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {8601--8605},
  year      = {2024},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2024/989},
  url       = {https://doi.org/10.24963/ijcai.2024/989},
}