Ordyniak, S orcid.org/0000-0003-1935-651X, Paesani, G and Szeider, S (Accepted: 2023) The Parameterized Complexity of Finding Concise Local Explanations. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. IJCAI 2023, The 32nd International Joint Conference On Artificial Intelligence, 19-25 Aug 2023, Macau, China. International Joint Conferences on Artificial Intelligence , pp. 3312-3320. ISBN 978-1-956792-03-4
Abstract
We consider the computational problem of finding a smallest local explanation (anchor) for classifying a given feature vector (example) by a black-box model. After showing that the problem is NP-hard in general, we study various natural restrictions of the problem in terms of problem parameters to see whether these restrictions make the problem fixed parameter tractable or not. We draw a detailed and systematic complexity landscape for combinations of parameters, including the size of the anchor, the size of the anchor’s coverage, and parameters that capture structural aspects of the problem instance, including rank-width, twin-width, and maximum difference.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Keywords: | Knowledge Representation and Reasoning, KRR, Computational complexity of reasoning Machine Learning, ML, Explainable/Interpretable machine learning |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EPSRC (Engineering and Physical Sciences Research Council) EP/V00252X/1 |
Depositing User: | Symplectic Publications |
Date Deposited: | 31 May 2023 11:25 |
Last Modified: | 08 Nov 2023 14:12 |
Published Version: | https://www.ijcai.org/proceedings/2023/369 |
Status: | Published |
Publisher: | International Joint Conferences on Artificial Intelligence |
Identification Number: | 10.24963/ijcai.2023/369 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:199661 |