Beyond Sparsity: Tree Regularization of Deep Models for Interpretability

Wu, Mike and Hughes, Michael C. and Parbhoo, Sonali and Zazzi, Maurizio and Roth, Volker and Doshi-Velez, Finale. (2018) Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18). pp. 1670-1678.

[img] PDF - Accepted Version

Official URL: https://edoc.unibas.ch/69173/

Downloads: Statistics Overview


The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little time. Specifically, we train deep time-series models so their class-probability predictions have high accuracy while being closely modeled by decision trees with few nodes. Using in- tuitive toy examples as well as medical tasks for treating sep- sis and HIV, we demonstrate that this new tree regularization yields models that are easier for humans to simulate than sim- pler L1 or L2 penalties without sacrificing predictive power.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Biomedical Data Analysis (Roth)
UniBasel Contributors:Roth, Volker and Parbhoo, Sonali
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Note:Publication type according to Uni Basel Research Database: Conference paper
Related URLs:
edoc DOI:
Last Modified:11 Jun 2019 11:43
Deposited On:05 Mar 2019 15:25

Repository Staff Only: item control page