Explaining random forests using bipolar argumentation and Markov networks

Potyka, Nico, Yin, Xiang and Toni, Francesca 2023. Explaining random forests using bipolar argumentation and Markov networks. Presented at: Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, 7-14 February 2023. Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023. AAAI Press, pp. 9453-9460. 10.1609/aaai.v37i8.26132

Preview

PDF - Published Version Download (192kB) | Preview

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. We show that their decision process can be naturally represented as an argumentation problem, which allows creating global explanations via argumentative reasoning. 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 present an efficient approximation algorithm with probabilistic approximation guarantees.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	AAAI Press
ISBN:	978-1-57735-880-0
Date of First Compliant Deposit:	19 October 2023
Last Modified:	08 Nov 2023 10:15
URI:	https://orca.cardiff.ac.uk/id/eprint/163313

Actions (repository staff only)

Edit Item