Circuit Representations of Random Forests with Applications to XAI

2026-02-09

AI Summary

This work addresses the interpretability of random forest classifiers by proposing a novel approach based on logic circuit compilation. It efficiently compiles random forests into class-specific Boolean circuits, enabling the exhaustive enumeration of various explanation types—including sufficient and necessary reasons, contrastive explanations, and shortest flip paths—through the integration of satisfiability-based reasoning and abstract interpretation techniques. To the best of our knowledge, this is the first method to unify and compute these diverse forms of explanations in an efficient and scalable manner. Empirical evaluation across multiple datasets demonstrates the practical utility and scalability of the approach for both explanation generation and decision robustness analysis.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Probabilistic Circuits and Graphical Models
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

We make three contributions in this paper. First, we present an approach for compiling a random forest classifier into a set of circuits, where each circuit directly encodes the instances in some class of the classifier. We show empirically that our proposed approach is significantly more efficient than existing similar approaches. Next, we utilize this approach to further obtain circuits that are tractable for computing the complete and general reasons of a decision, which are instance abstractions that play a fundamental role in computing explanations. Finally, we propose algorithms for computing the robustness of a decision and all shortest ways to flip it. We illustrate the utility of our contributions by using them to enumerate all sufficient reasons, necessary reasons and contrastive explanations of decisions; to compute the robustness of decisions; and to identify all shortest ways to flip the decisions made by random forest classifiers learned from a wide range of datasets.

Problem

• Random Forests
• Explainable AI
• Decision Robustness
• Sufficient Reasons
• Contrastive Explanations

Innovation

• circuit compilation
• random forests
• explainable AI
• decision robustness
• contrastive explanations