Rigorous Explanations for Tree Ensembles
This addresses the need for trustworthy AI in decision-making by providing verifiable explanations for complex models, though it is incremental as it focuses on specific tree ensemble types.
The paper tackles the problem of making tree ensembles like random forests and boosted trees interpretable by computing rigorous, logically-sound explanations for their predictions, ensuring these explanations accurately reflect the underlying model's properties.
Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accurate classes of machine learning methods. While they are typically quite concise in representation, their operation remains inscrutable to human decision makers. One solution to build trust in the operation of TEs is to automatically identify explanations for the predictions made. Evidently, we can only achieve trust using explanations, if those explanations are rigorous, that is truly reflect properties of the underlying predictor they explain This paper investigates the computation of rigorously-defined, logically-sound explanations for the concrete case of two well-known examples of tree ensembles, namely random forests and boosted trees.