DeepSaDe: Learning Neural Networks That Guarantee Domain Constraint Satisfaction

Kshitij Goyal, Sebastijan Dumancic, Hendrik Blockeel

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, especially in safety-critical applications, e.g., actions of an autonomous vehicle must be safe. There are approaches that can train neural networks where such domain requirements are enforced as constraints, but they either cannot guarantee that the constraint will be satisfied by all possible predictions (even on unseen data) or they are limited in the type of constraints that can be enforced. In this work, we present an approach to train neural networks which can enforce a wide variety of constraints and guarantee that the constraint is satisfied by all possible predictions. The approach builds on earlier work where learning linear models is formulated as a constraint satisfaction problem (CSP). To make this idea applicable to neural networks, two crucial new elements are added: constraint propagation over the network layers, and weight updates based on a mix of gradient descent and CSP solving. Evaluation on various machine learning tasks demonstrates that our approach is flexible enough to enforce a wide variety of domain constraints and is able to guarantee them in neural networks.

Original languageEnglish
Title of host publicationTechnical Tracks 14
EditorsMichael Wooldridge, Jennifer Dy, Sriraam Natarajan
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Pages12199-12207
Number of pages9
Volume38
Edition11
ISBN (Electronic)1577358872, 9781577358879
DOIs
Publication statusPublished - 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number11
Volume38
ISSN (Print)2159-5399
ISSN (Electronic)2374-3468

Conference

Conference38th AAAI Conference on Artificial Intelligence, AAAI 2024
Country/TerritoryCanada
CityVancouver
Period20/02/2427/02/24

Bibliographical note

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Fingerprint

Dive into the research topics of 'DeepSaDe: Learning Neural Networks That Guarantee Domain Constraint Satisfaction'. Together they form a unique fingerprint.

Cite this