# Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization

arXiv: https://arxiv.org/abs/1904.05394 · HTML: https://mlsanity.com/paper/1904.05394/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning](https://mlsanity.com/paper/2202.11954/) (2022)
- [DINE: Dimensional Interpretability of Node Embeddings](https://mlsanity.com/paper/2310.01162/) (2023)
- [A Survey of Neural Trees](https://mlsanity.com/paper/2209.03415/) (2022)
- [Logical Distillation of Graph Neural Networks](https://mlsanity.com/paper/2406.07126/) (2024)
- [DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees](https://mlsanity.com/paper/2205.13234/) (2022)
- [Scale-Preserving Automatic Concept Extraction (SPACE)](https://mlsanity.com/paper/2308.06022/) (2023)
- [NN2Rules: Extracting Rule List from Neural Networks](https://mlsanity.com/paper/2207.12271/) (2022)
- [Interpreting Neural Policies with Disentangled Tree Representations](https://mlsanity.com/paper/2210.06650/) (2022)
- [Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates](https://mlsanity.com/paper/2310.04352/) (2023)

## Abstract (arXiv)

One obstacle that so far prevents the introduction of machine learning models primarily in critical areas is the lack of explainability. In this work, a practicable approach of gaining explainability of deep artificial neural networks (NN) using an interpretable surrogate model based on decision trees is presented. Simply fitting a decision tree to a trained NN usually leads to unsatisfactory results in terms of accuracy and fidelity. Using L1-orthogonal regularization during training, however, preserves the accuracy of the NN, while it can be closely approximated by small decision trees. Tests with different data sets confirm that L1-orthogonal regularization yields models of lower complexity and at the same time higher fidelity compared to other regularizers.