The beta version of DROPS 2 is now publicly available! Check this page out at DROPS 2 now!


License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.CP.2023.38
URN: urn:nbn:de:0030-drops-190758
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2023/19075/
Go to the corresponding LIPIcs Volume Portal

Yu, Jinqiang ; Ignatiev, Alexey ; Stuckey, Peter J.

From Formal Boosted Tree Explanations to Interpretable Rule Sets

pdf-format:
LIPIcs-CP-2023-38.pdf (4 MB)

Abstract

The rapid rise of Artificial Intelligence (AI) and Machine Learning (ML) has invoked the need for explainable AI (XAI). One of the most prominent approaches to XAI is to train rule-based ML models, e.g. decision trees, lists and sets, that are deemed interpretable due to their transparent nature. Recent years have witnessed a large body of work in the area of constraints- and reasoning-based approaches to the inference of interpretable models, in particular decision sets (DSes). Despite being shown to outperform heuristic approaches in terms of accuracy, most of them suffer from scalability issues and often fail to handle large training data, in which case no solution is offered. Motivated by this limitation and the success of gradient boosted trees, we propose a novel anytime approach to producing DSes that are both accurate and interpretable. The approach makes use of the concept of a generalized formal explanation and builds on the recent advances in formal explainability of gradient boosted trees. Experimental results obtained on a wide range of datasets, demonstrate that our approach produces DSes that more accurate than those of the state-of-the-art algorithms and comparable with them in terms of explanation size.

BibTeX - Entry

@InProceedings{yu_et_al:LIPIcs.CP.2023.38,
  author =	{Yu, Jinqiang and Ignatiev, Alexey and Stuckey, Peter J.},
  title =	{{From Formal Boosted Tree Explanations to Interpretable Rule Sets}},
  booktitle =	{29th International Conference on Principles and Practice of Constraint Programming (CP 2023)},
  pages =	{38:1--38:21},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-300-3},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{280},
  editor =	{Yap, Roland H. C.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2023/19075},
  URN =		{urn:nbn:de:0030-drops-190758},
  doi =		{10.4230/LIPIcs.CP.2023.38},
  annote =	{Keywords: Decision set, interpretable model, gradient boosted tree, BT compilation}
}

Keywords: Decision set, interpretable model, gradient boosted tree, BT compilation
Collection: 29th International Conference on Principles and Practice of Constraint Programming (CP 2023)
Issue Date: 2023
Date of publication: 22.09.2023
Supplementary Material: Software (Source Code): https://github.com/jinqiang-yu/cpl/ archived at: https://archive.softwareheritage.org/swh:1:dir:40fde451a732a518f78caa9ad372a7c267446836

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI