An Efficient Compilation-Based Approach to Explaining Random Forests Through Decision Trees

Alnis Murtovi, Maximilian Schlüter, Bernhard Steffen

2025

Abstract

Tree-based ensemble methods like Random Forests often outperform deep learning models on tabular datasets but suffer from a lack of interpretability due to their complex structures. Existing explainability techniques either offer approximate explanations or face scalability issues with large models. In this paper, we introduce a novel compilation-based approach that transforms Random Forests into single, semantically equivalent decision trees through a recursive process enhanced with optimizations and heuristics. Our empirical evaluation demonstrates that our approach is over an order of magnitude faster than current state-of-the-art compilation-based methods while producing decision trees of comparable size.

Paper Citation

in Harvard Style

Murtovi A., Schlüter M. and Steffen B. (2025). An Efficient Compilation-Based Approach to Explaining Random Forests Through Decision Trees. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 484-495. DOI: 10.5220/0013188600003890

in Bibtex Style

@conference{icaart25,
author={Alnis Murtovi and Maximilian Schlüter and Bernhard Steffen},
title={An Efficient Compilation-Based Approach to Explaining Random Forests Through Decision Trees},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={484-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013188600003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - An Efficient Compilation-Based Approach to Explaining Random Forests Through Decision Trees
SN - 978-989-758-737-5
AU - Murtovi A.
AU - Schlüter M.
AU - Steffen B.
PY - 2025
SP - 484
EP - 495
DO - 10.5220/0013188600003890
PB - SciTePress