ICML 2019oral71 citations

Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute

Tong Wang

Abstract

This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case. Our solution is to find an interpretable substitute on a subset of data where the black-box model is

BibTeX
@InProceedings{pmlr-v97-wang19a,
  title = 	 {Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute},
  author =       {Wang, Tong},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {6505--6514},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/wang19a/wang19a.pdf},
  url = 	 {https://proceedings.mlr.press/v97/wang19a.html},
  abstract = 	 {This work addresses the situation where a black-box model with good predictive performance is chosen over its interpretable competitors, and we show interpretability is still achievable in this case. Our solution is to find an interpretable substitute on a subset of data where the black-box model is
Gaining Free or Low-Cost Interpretability with Interpretable Partial Substitute · ICML 2019