Towards robust contrastive explanations for human-neural multi-agent systems
File(s)
Accepted version
Author(s)
Leofante, Francesco
Lomuscio, Alessio
Type
Conference Paper
Abstract
Generating explanations of high quality is fundamental to the development of trustworthy human-AI interactions. We here study the problem of generating contrastive explanations with formal robustness guarantees. We formalise a new notion of robustness and introduce two novel verification-based algorithms to (i) identify non-robust explanations generated by other methods and (ii) generate contrastive explanations augmented with provable
robustness certificates. We present an implementation and evaluate the utility of the approach on two case studies concerning neural agents trained
on credit scoring and image classification tasks.
robustness certificates. We present an implementation and evaluate the utility of the approach on two case studies concerning neural agents trained
on credit scoring and image classification tasks.
Date Issued
2023-05-30
Date Acceptance
2023-01-04
Citation
Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems, 2023, pp.2343-2345
Publisher
ACM
Start Page
2343
End Page
2345
Journal / Book Title
Proceedings of the 22nd International Conference on Autonomous Agents and Multiagent Systems
Copyright Statement
© 2023 International Foundation for Autonomous Agents
and Multiagent Systems (www.ifaamas.org). All rights reserved.
and Multiagent Systems (www.ifaamas.org). All rights reserved.
Identifier
https://dl.acm.org/doi/10.5555/3545946.3598928
Source
International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)
Publication Status
Published
Start Date
2023-05-29
Finish Date
2023-06-02
Coverage Spatial
London, UK
Date Publish Online
2023-05-30