From formal boosted tree explanations to interpretable rule sets

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


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.

Original languageEnglish
Title of host publication29th International Conference on Principles and Practice of Constraint Programming
EditorsRoland H. C. Yap
Place of PublicationWadern Germany
PublisherSchloss Dagstuhl
Number of pages21
ISBN (Electronic)9783959773003
Publication statusPublished - Sept 2023
EventInternational Conference on Principles and Practice of Constraint Programming 2023 - Toronto, Canada
Duration: 27 Aug 202331 Aug 2023
Conference number: 29th (Proceedings) (Website)


ConferenceInternational Conference on Principles and Practice of Constraint Programming 2023
Abbreviated titleCP 2023
Internet address


  • BT compilation
  • Decision set
  • gradient boosted tree
  • interpretable model

Cite this