Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming
Open Access
- 1 September 2024
- journal article
- research article
- Published by Cambridge University Press (CUP) in Theory and Practice of Logic Programming
- Vol. 24 (5) , 973-1010
Abstract
We propose a method for generating rule sets as global and local explanations for tree-ensemble learning methods using answer set programming (ASP). To this end, we adopt a decompositional approach where the split structures of the base decision trees are exploited in the construction of rules, which in turn are assessed using pattern mining methods encoded in ASP to extract explanatory rules. For global explanations, candidate rules are chosen from the entire trained tree-ensemble models, whereas for local explanations, candidate rules are selected by only considering rules that are relevant to the particular predicted instance. We show how user-defined constraints and preferences can be represented declaratively in ASP to allow for transparent and flexible rule set generation, and how rules can be used as explanations to help the user better understand the models. Experimental evaluation with real-world datasets and popular tree-ensemble algorithms demonstrates that our approach is applicable to a wide range of classification tasks.Keywords
This publication has 28 references indexed in Scilit:
- On the explanatory power of Boolean decision treesData & Knowledge Engineering, 2022
- Computing Optimal Decision Sets with SAT2020
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- Hybrid ASP-based Approach to Pattern MiningTheory and Practice of Logic Programming, 2019
- Interpreting tree ensembles with inTreesInternational Journal of Data Science and Analytics, 2018
- Itemset mining: A constraint programming perspectiveArtificial Intelligence, 2011
- An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive modelsDecision Support Systems, 2011
- Itemset Mining as a Challenge Application for Answer Set EnumerationLecture Notes in Computer Science, 2011
- Random ForestsMachine Learning, 2001
- Fast Effective Rule Induction1995