A posteriori verification or a priori design? Navigating requirements-driven deep learning
File(s)
Published version
Author(s)
Giunchiglia, Eleonora
Type
Conference Paper
Abstract
As machine learning systems are increasingly deployed in settings where correctness, safety, and alignment with domain-specific requirements are critical, ensuring that models satisfy formal properties has become a central challenge. Two main paradigms have emerged to address this problem: a priori design, where logical or structural requirements are integrated directly into the model’s architecture or training process, and a posteriori verification, where trained models are analyzed to determine whether they satisfy desired properties. In this position paper, I argue that these approaches are not competing, but rather complementary. Wherever possible, requirements should be enforced by design, ensuring correctness by construction and reducing the verification burden. Recent advances—–ranging from differentiable requirements-aware layers and loss functions to full neurosymbolic models—–demonstrate the feasibility and benefits of this approach. However, not all requirements are easily expressible in a differentiable or learnable form, and in such cases, verification remains essential for certifying model behavior post hoc. This is particularly relevant for complex global properties, interactions between components, or constraints introduced after training. This paper provides an overview over the progress made on both fronts, while identifying practical trade-offs in expressivity, scalability, and trustworthiness. It is also a call for a unified research agenda that treats verification and design as interdependent tools in the development of reliable learning systems. The position provided in the paper is clear: whatever can be enforced by design, should be—while verification should serve as a safety net where design falls short.
Date Issued
2025-10-21
Date Acceptance
2025-10-01
Citation
Frontiers in Artificial Intelligence and Applications, 2025, 413
ISBN
978-1-64368-631-8
ISSN
0922-6389
Publisher
IOS Press
Start Page
30
End Page
37
Journal / Book Title
Frontiers in Artificial Intelligence and Applications
Volume
413
Copyright Statement
© 2025 The Authors. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0).
License URL
Source
ECAI 2025
Publication Status
Published
Start Date
2025-10-25
Finish Date
2025-10-30
Coverage Spatial
Bologna, Italy