PiShield: A PyTorch Package for Learning with Requirements

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' top...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-05
Main Authors: Stoian, Mihaela Cătălina, Tatomir, Alex, Lukasiewicz, Thomas, Giunchiglia, Eleonora
Format: Article
Language:English
Subjects:
Deep learning
Domains
Neural networks
Tables (data)
Topology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422