CE-QArg: Counterfactual explanations for quantitative bipolar argumentation frameworks

Yin, Xiang, Potyka, Nico and Toni, Francesca 2024. CE-QArg: Counterfactual explanations for quantitative bipolar argumentation frameworks. Presented at: 21st International Conference on Principles of Knowledge Representation and Reasoning (KR 2024), Hanoi, Vietnam, 2-8 November 2024. Published in: Marquis, Pierre, Ortiz, Magdalena and Pagnucco, Maurice eds. Proceedings of the 21st International Conference on Principles of Knowledge Representation and Reasoning — Main Track. International Joint Conferences on Artificial Intelligence Organization, pp. 697-707. 10.24963/kr.2024/66

Preview

PDF - Accepted Post-Print Version Download (1MB) | Preview

Abstract

There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by assigning importance scores to other arguments but fail to explain how to change the current strength to a desired one. To solve this issue, we introduce counterfactual explanations for QBAFs. We discuss problem variants and propose an iterative algorithm named Counterfactual Explanations for Quantitative bipolar Argumentation frameworks (CE-QArg). CE-QArg can identify valid and cost-effective counterfactual explanations based on two core modules, polarity and priority, which help determine the updating direction and magnitude for each argument, respectively. We discuss some formal properties of our counterfactual explanations and empirically evaluate CE-QArg on randomly generated QBAFs.

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Computer Science & Informatics
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Publisher:	International Joint Conferences on Artificial Intelligence Organization
ISBN:	9781956792058
ISSN:	2334-1033
Date of First Compliant Deposit:	14 October 2024
Date of Acceptance:	11 July 2024
Last Modified:	07 Nov 2024 11:44
URI:	https://orca.cardiff.ac.uk/id/eprint/172863

Actions (repository staff only)

Edit Item