Multi-label classification neural networks with hard logical constraints
Author(s)
Giunchiglia, Eleonora
Lukasiewicz, Thomas
Type
Journal Article
Abstract
Multi-label classification (MC) is a standard machine learning problem in which a data point can be associated with a set of classes. A more challenging scenario is given by hierarchical multi-label classification (HMC) problems, in which every prediction must satisfy a given set of hard constraints expressing subclass relationships between classes. In this article, we propose C-HMCNN(h), a novel approach for solving HMC problems, which, given a network h for the underlying MC problem, exploits the hierarchy information in order to produce predictions coherent with the constraints and to improve performance. Furthermore, we extend the logic used to express HMC constraints in order to be able to specify more complex relations among the classes and propose a new model CCN(h), which extends C-HMCNN(h) and is again able to satisfy and exploit the constraints to improve performance. We conduct an extensive experimental analysis showing the superior performance of both C-HMCNN(h) and CCN(h) when compared to state-of-the-art models in both the HMC and the general MC setting with hard logical constraints.
Date Issued
2021-11-01
Date Acceptance
2021-03-01
Citation
The journal of artificial intelligence research, 2021, 72, pp.759-818
ISSN
1076-9757
Publisher
AI Access Foundation
Start Page
759
End Page
818
Journal / Book Title
The journal of artificial intelligence research
Volume
72
Copyright Statement
©2021 AI Access Foundation. All rights reserved. This article is are available under the terms of the JAIR License Version 1, https://www.jair.org/index.php/jair/oldlicense
Subjects
Computer Science
Computer Science, Artificial Intelligence
ENSEMBLES
HIERARCHICAL-CLASSIFICATION
PREDICTION
Science & Technology
SEQUENCE
Technology
Publication Status
Published