Circuit Representations of Random Forests with Applications to XAI

Researchers developed a new method for converting random forest classifiers into circuit representations that enables more efficient computation of decision explanations. The approach provides tools for computing robustness metrics and identifying ways to alter classifier decisions, with applications in explainable AI (XAI).

• →New circuit-based approach for random forest classifiers is significantly more efficient than existing methods.
• →The method enables computation of complete and general reasons behind AI decision-making.
• →Algorithms were developed to measure decision robustness and identify shortest paths to flip decisions.
• →The approach can enumerate sufficient reasons, necessary reasons, and contrastive explanations for AI decisions.
• →Implementation was tested across multiple datasets demonstrating practical utility for explainable AI applications.