Malmqvist, Lars, Yuan, Tommy and Nightingale, Peter orcid.org/0000-0002-5052-8634 (2024) Approximating Problems in Abstract Argumentation with Graph Convolutional Networks. Artificial Intelligence. 104209. ISSN 0004-3702
Abstract
In this article, we present a novel approximation approach for abstract argumentation using a customized Graph Convolutional Network (GCN) architecture and a tailored training method. Our approach demonstrates promising results in approximating abstract argumentation tasks across various semantics, setting a new state of the art for performance on certain tasks. We provide a detailed analysis of approximation and runtime performance and propose a new scheme for evaluation. By advancing the state of the art for approximating the acceptability status of abstract arguments, we make theoretical and empirical advances in understanding the limits and opportunities for approximation in this field. Our approach shows potential for creating both general purpose and task-specific approximators and offers insights into the performance differences across benchmarks and semantics.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 The Author(s). |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Funding Information: | Funder Grant number EPSRC EP/W001977/1 |
Depositing User: | Pure (York) |
Date Deposited: | 29 Aug 2024 13:00 |
Last Modified: | 02 Jan 2025 10:10 |
Published Version: | https://doi.org/10.1016/j.artint.2024.104209 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1016/j.artint.2024.104209 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:216560 |
Download
Filename: 1-s2.0-S0004370224001450-main.pdf
Description: 1-s2.0-S0004370224001450-main
Licence: CC-BY 2.5