Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularization
This work addresses the lack of explainability in machine learning for critical areas, though it appears incremental as it builds on existing surrogate model methods.
The paper tackles the problem of making deep neural networks more interpretable by using L1-orthogonal regularization to enable accurate approximation with small decision trees, resulting in models with lower complexity and higher fidelity compared to other regularizers.
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.