Year: 2023
Type: conference-paper
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.
DOI: 10.24963/kr.2023/78
Institutions: Imperial College London, University of Kent
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4385437649
