Anchors: High-Precision Model-Agnostic Explanations

Abstract

We introduce a novel model-agnostic system that explains the behavior of complex models with high-precision rules called anchors, representing local, "sufficient" conditions for predictions. We propose an algorithm to efficiently compute these explanations for any black-box model with high-probability guarantees. We demonstrate the flexibility of anchors by explaining a myriad of different models for different domains and tasks. In a user study, we show that anchors enable users to predict how a model would behave on unseen instances with less effort and higher precision, as compared to existing linear explanations or no explanations.

Cite

Text

Ribeiro et al. "Anchors: High-Precision Model-Agnostic Explanations." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11491

Markdown

[Ribeiro et al. "Anchors: High-Precision Model-Agnostic Explanations." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/ribeiro2018aaai-anchors/) doi:10.1609/AAAI.V32I1.11491

BibTeX

@inproceedings{ribeiro2018aaai-anchors,
  title     = {{Anchors: High-Precision Model-Agnostic Explanations}},
  author    = {Ribeiro, Marco Túlio and Singh, Sameer and Guestrin, Carlos},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {1527-1535},
  doi       = {10.1609/AAAI.V32I1.11491},
  url       = {https://mlanthology.org/aaai/2018/ribeiro2018aaai-anchors/}
}