Regional Tree Regularization for Interpretability in Deep Neural Networks

The lack of interpretability remains a barrier to adopting deep neural networks across many safety-critical domains. Tree regularization was recently proposed to encourage a deep neural network's decisions to resemble those of a globally compact, axis-aligned decision tree. However, it is often...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... AAAI Conference on Artificial Intelligence 2020-04, Vol.34 (4), p.6413-6421
Main Authors: Wu, Mike, Parbhoo, Sonali, Hughes, Michael, Kindle, Ryan, Celi, Leo, Zazzi, Maurizio, Roth, Volker, Doshi-Velez, Finale
Format: Article
Language:English
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The lack of interpretability remains a barrier to adopting deep neural networks across many safety-critical domains. Tree regularization was recently proposed to encourage a deep neural network's decisions to resemble those of a globally compact, axis-aligned decision tree. However, it is often unreasonable to expect a single tree to predict well across all possible inputs. In practice, doing so could lead to neither interpretable nor performant optima. To address this issue, we propose regional tree regularization – a method that encourages a deep model to be well-approximated by several separate decision trees specific to predefined regions of the input space. Across many datasets, including two healthcare applications, we show our approach delivers simpler explanations than other regularization schemes without compromising accuracy. Specifically, our regional regularizer finds many more “desirable” optima compared to global analogues.
ISSN:2159-5399
2374-3468
DOI:10.1609/aaai.v34i04.6112