Counterfactual Metarules for Local and Global Recourse

Abstract

We introduce T-CREx, a novel model-agnostic method for local and global counterfactual explanation (CE), which summarises recourse options for both individuals and groups in the form of generalised rules. It leverages tree-based surrogate models to learn the counterfactual rules, alongside metarules denoting their regimes of optimality, providing both a global analysis of model behaviour and diverse recourse options for users. Experiments indicate that T-CREx achieves superior aggregate performance over existing rule-based baselines on a range of CE desiderata, while being orders of magnitude faster to run.

Cite

Text

Bewley et al. "Counterfactual Metarules for Local and Global Recourse." International Conference on Machine Learning, 2024.

Markdown

[Bewley et al. "Counterfactual Metarules for Local and Global Recourse." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/bewley2024icml-counterfactual/)

BibTeX

@inproceedings{bewley2024icml-counterfactual,
  title     = {{Counterfactual Metarules for Local and Global Recourse}},
  author    = {Bewley, Tom and Amoukou, Salim I. and Mishra, Saumitra and Magazzeni, Daniele and Veloso, Manuela},
  booktitle = {International Conference on Machine Learning},
  year      = {2024},
  pages     = {3707-3724},
  volume    = {235},
  url       = {https://mlanthology.org/icml/2024/bewley2024icml-counterfactual/}
}