RuleExplorer: A Scalable Matrix Visualization for Understanding Tree Ensemble Classifiers
This addresses interpretability challenges for users of tree ensemble classifiers in real-world applications, though it is an incremental improvement over existing visualization approaches.
The paper tackles the problem of understanding complex tree ensemble classifiers with tens of thousands of rules, where existing methods lose fidelity by reducing rule sets. It introduces a scalable visual analysis method that organizes rules hierarchically and prioritizes anomalous rules, enhancing interpretability without sacrificing comprehensiveness.
The high performance of tree ensemble classifiers benefits from a large set of rules, which, in turn, makes the models hard to understand. To improve interpretability, existing methods extract a subset of rules for approximation using model reduction techniques. However, by focusing on the reduced rule set, these methods often lose fidelity and ignore anomalous rules that, despite their infrequency, play crucial roles in real-world applications. This paper introduces a scalable visual analysis method to explain tree ensemble classifiers that contain tens of thousands of rules. The key idea is to address the issue of losing fidelity by adaptively organizing the rules as a hierarchy rather than reducing them. To ensure the inclusion of anomalous rules, we develop an anomaly-biased model reduction method to prioritize these rules at each hierarchical level. Synergized with this hierarchical organization of rules, we develop a matrix-based hierarchical visualization to support exploration at different levels of detail. Our quantitative experiments and case studies demonstrate how our method fosters a deeper understanding of both common and anomalous rules, thereby enhancing interpretability without sacrificing comprehensiveness.