PiShield: A PyTorch Package for Learning with Requirements
This addresses the need for safety in deep learning applications across various domains, though it appears incremental as it builds on existing package-based solutions.
The authors tackled the problem of deep learning models failing to meet safety requirements by introducing PiShield, a PyTorch package that integrates requirements into neural network topologies, guaranteeing compliance regardless of input and enabling application in domains like functional genomics, autonomous driving, and tabular data generation.
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.