Conceptual Views on Tree Ensemble Classifiers
This work addresses the loss of explainability in popular tree-based methods, which is a problem for users needing interpretable AI, though it appears incremental as it builds on existing statistical methods.
The authors tackled the problem of explainability in tree ensemble classifiers like Random Forests by proposing an algebraic method based on lattice theory for global explanation, demonstrating its capabilities on standard Random Forest models.
Random Forests and related tree-based methods are popular for supervised learning from table based data. Apart from their ease of parallelization, their classification performance is also superior. However, this performance, especially parallelizability, is offset by the loss of explainability. Statistical methods are often used to compensate for this disadvantage. Yet, their ability for local explanations, and in particular for global explanations, is limited. In the present work we propose an algebraic method, rooted in lattice theory, for the (global) explanation of tree ensembles. In detail, we introduce two novel conceptual views on tree ensemble classifiers and demonstrate their explanatory capabilities on Random Forests that were trained with standard parameters.