On Symbolically Encoding the Behavior of Random Forests
This work addresses the need for explainable AI by providing a method to compute prime implicants for random forests, which is incremental as it extends symbolic encoding techniques to more complex systems.
The paper tackled the problem of symbolically encoding the behavior of random forests with discrete inputs and outputs, including discretized continuous variables, and proposed an encoding that is sound and complete for computing prime implicants to explain decisions.
Recent work has shown that the input-output behavior of some machine learning systems can be captured symbolically using Boolean expressions or tractable Boolean circuits, which facilitates reasoning about the behavior of these systems. While most of the focus has been on systems with Boolean inputs and outputs, we address systems with discrete inputs and outputs, including ones with discretized continuous variables as in systems based on decision trees. We also focus on the suitability of encodings for computing prime implicants, which have recently played a central role in explaining the decisions of machine learning systems. We show some key distinctions with encodings for satisfiability, and propose an encoding that is sound and complete for the given task.