Explaining Random Forests using Bipolar Argumentation and Markov Networks (Technical Report)

TL;DR

This paper introduces a novel approach to interpret random forests by representing their decision processes as argumentation problems using bipolar argumentation and Markov networks, providing explanations and approximations.

Contribution

It generalizes argumentative explanations for random forests with a Markov network encoding and proposes a probabilistic approximation algorithm for complex explanation tasks.

Findings

Proposed a Markov network-based explanation framework.

Developed a probabilistic approximation algorithm.

Presented initial experimental results demonstrating effectiveness.

Abstract

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.