Principled Diverse Counterfactuals in Multilinear Models

Abstract

Machine learning (ML) applications have automated numerous real-life tasks, improving both private and public life. However, the black-box nature of many state-of-the-art models poses the challenge of model verification; how can one be sure that the algorithm bases its decisions on the proper criteria, or that it does not discriminate against certain minority groups? In this paper we propose a way to generate diverse counterfactual explanations from multilinear models, a broad class which includes Random Forests, as well as Bayesian Networks.

Cite

Text

Papantonis and Belle. "Principled Diverse Counterfactuals in Multilinear Models." Machine Learning, 2024. doi:10.1007/S10994-023-06411-Z

Markdown

[Papantonis and Belle. "Principled Diverse Counterfactuals in Multilinear Models." Machine Learning, 2024.](https://mlanthology.org/mlj/2024/papantonis2024mlj-principled/) doi:10.1007/S10994-023-06411-Z

BibTeX

@article{papantonis2024mlj-principled,
  title     = {{Principled Diverse Counterfactuals in Multilinear Models}},
  author    = {Papantonis, Ioannis and Belle, Vaishak},
  journal   = {Machine Learning},
  year      = {2024},
  pages     = {1421-1443},
  doi       = {10.1007/S10994-023-06411-Z},
  volume    = {113},
  url       = {https://mlanthology.org/mlj/2024/papantonis2024mlj-principled/}
}