Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)
This addresses interpretability for users of random forests, but it is incremental as it builds on existing abductive explanation methods.
The paper tackles the problem of incomprehensibility in random forest decision-making by representing it as an argumentation problem using Markov networks, and presents a probabilistic approximation algorithm with initial experimental results.
Random forests are decision tree ensembles that can be used to solve a variety of machine learning problems. However, as the number of trees and their individual size can be large, their decision making process is often incomprehensible. In order to reason about the decision process, we propose representing it as an argumentation problem. We generalize sufficient and necessary argumentative explanations using a Markov network encoding, discuss the relevance of these explanations and establish relationships to families of abductive explanations from the literature. As the complexity of the explanation problems is high, we discuss a probabilistic approximation algorithm and present first experimental results.