PiShield: a PyTorch package for learning with requirements
File(s)
Accepted version
OA Location
Author(s)
Stoian, Mihaela C
Tatomir, Alex
Lukasiewicz, Thomas
Giunchiglia, Eleonora
Type
Conference Paper
Abstract
Deep learning models have shown their strengths in various application domains, however, they often struggle to meet safety requirements for their outputs. In this paper, we introduce PiShield, the first package ever allowing for the integration of the requirements into the neural networks' topology. PiShield guarantees compliance with these requirements, regardless of input. Additionally, it allows for integrating requirements both at inference and/or training time, depending on the practitioners' needs. Given the widespread application of deep learning, there is a growing need for frameworks allowing for the integration of the requirements across various domains. Here, we explore three application scenarios: functional genomics, autonomous driving, and tabular data generation.
Date Issued
2024-08-03
Date Acceptance
2024-08-01
Citation
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence, 2024, pp.8805-8809
Publisher
International Joint Conferences on Artificial Intelligence Organization
Start Page
8805
End Page
8809
Journal / Book Title
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence
Copyright Statement
Copyright © 2024 International Joint Conferences on Artificial Intelligence All rights reserved. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
(https://creativecommons.org/licenses/by/4.0/
Source
Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}
Publication Status
Published
Start Date
2023-08-03
Finish Date
2023-08-09
Coverage Spatial
Jeju, Korea