Skip to main content
Kent Academic Repository

Counterfactual explanations and model multiplicity: a relational verification view

Leofante, Francesco, Botoeva, Elena, Rajani, Vineet (2023) Counterfactual explanations and model multiplicity: a relational verification view. In: Proceedings of the 20th International Conference on Principles of Knowledge Representation and Reasoning. . pp. 763-768. IJCAI ISBN 978-1-956792-02-7. (doi:10.24963/kr.2023/78) (KAR id:112768)

PDF Author's Accepted Manuscript
Language: English
Download this file
(PDF/356kB)
[thumbnail of kr23.pdf]
Preview
Request a format suitable for use with assistive technology e.g. a screenreader
PDF Publisher pdf
Language: English

Restricted to Repository staff only
Contact us about this publication
[thumbnail of kr2023-0078-leofante-et-al.pdf]
Official URL:
https://doi.org/10.24963/kr.2023/78
Additional URLs:

Abstract

We study the interplay between counterfactual explanations and model multiplicity in the context of neural network classifiers. We show that current explanation methods often produce counterfactuals whose validity is not preserved under model multiplicity. We then study the problem of generating counterfactuals that are guaranteed to be robust to model multiplicity, characterise its complexity and propose an approach to solve this problem using ideas from relational verification.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.24963/kr.2023/78
Uncontrolled keywords: counterfactual explanations, model multiplicity, neural networks, explainable AI
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Institutional Unit: Schools > School of Computing
Former Institutional Unit:
There are no former institutional units.
Funders: University of Kent (https://ror.org/00xkeyj56)
Depositing User: Elena Botoeva
Date Deposited: 16 Jan 2026 18:09 UTC
Last Modified: 21 Jan 2026 03:46 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/112768 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views of this page since July 2020. For more details click on the image.