Generating Global and Local Explanations for Tree-Ensemble Learning Methods by Answer Set Programming
This work addresses the need for transparent and flexible explanations in machine learning models, particularly for users of tree-ensemble methods, though it appears incremental as it builds on existing decompositional and pattern mining approaches.
The authors tackled the problem of explaining tree-ensemble learning methods by proposing a method that uses Answer Set Programming (ASP) to generate rule sets for global and local explanations, demonstrating applicability across various classification tasks with real-world datasets.
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. Under consideration in Theory and Practice of Logic Programming (TPLP).