# Optimizing for Interpretability in Deep Neural Networks with Tree Regularization

arXiv: https://arxiv.org/abs/1908.05254 · HTML: https://mlsanity.com/paper/1908.05254/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Interpretable by Design: Learning Predictors by Composing Interpretable Queries](https://mlsanity.com/paper/2207.00938/) (2022)
- [Variational Information Pursuit for Interpretable Predictions](https://mlsanity.com/paper/2302.02876/) (2023)
- [SpArX: Sparse Argumentative Explanations for Neural Networks [Technical Report]](https://mlsanity.com/paper/2301.09559/) (2023)
- [Generating Synthetic Clinical Data that Capture Class Imbalanced Distributions with Generative Adversarial Networks: Example using Antiretroviral Therapy for HIV](https://mlsanity.com/paper/2208.08655/) (2022)
- [A Survey of Neural Trees](https://mlsanity.com/paper/2209.03415/) (2022)
- [3VL: Using Trees to Improve Vision-Language Models' Interpretability](https://mlsanity.com/paper/2312.17345/) (2023)
- [Interpreting Neural Policies with Disentangled Tree Representations](https://mlsanity.com/paper/2210.06650/) (2022)
- [Arithmetical Binary Decision Tree Traversals](https://mlsanity.com/paper/2209.04825/) (2022)
- [Interpretable Deep Tracking](https://mlsanity.com/paper/2210.01266/) (2022)
- [A priori Estimates for Deep Residual Network in Continuous-time Reinforcement Learning](https://mlsanity.com/paper/2402.16899/) (2024)
- [Smooth InfoMax -- Towards Easier Post-Hoc Interpretability](https://mlsanity.com/paper/2408.12936/) (2024)
- [NIMO: a Nonlinear Interpretable MOdel](https://mlsanity.com/paper/2506.05059/) (2025)

## Abstract (arXiv)

Deep models have advanced prediction in many domains, but their lack of interpretability remains a key barrier to the adoption in many real world applications. There exists a large body of work aiming to help humans understand these black box functions to varying levels of granularity -- for example, through distillation, gradients, or adversarial examples. These methods however, all tackle interpretability as a separate process after training. In this work, we take a different approach and explicitly regularize deep models so that they are well-approximated by processes that humans can step-through in little time. Specifically, we train several families of deep neural networks to resemble compact, axis-aligned decision trees without significant compromises in accuracy. The resulting axis-aligned decision functions uniquely make tree regularized models easy for humans to interpret. Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts. Using intuitive toy examples as well as medical tasks for patients in critical care and with HIV, we demonstrate that this new family of tree regularizers yield models that are easier for humans to simulate than simpler L1 or L2 penalties without sacrificing predictive power.