Classifier-based constraint acquisition

• Published in: Annals of mathematics and artificial intelligence Vol. 89; no. 7; pp. 655 - 674
• Main Authors: Prestwich, S. D., Freuder, E. C., O’Sullivan, B., Browne, D.
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01.07.2021; Springer; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Automation; Classifiers; Combinatorial analysis; Complex Systems; Computer Science; Constraint modelling; Data science; Datasets; Decision trees; Information technology; Logic programming; Machine learning; Mathematics; Methods; Neural networks; Variables; 68T99; 68R99; Bayesian; Constraint acquisition; Classifier; Boolean satisfiability; 68Q32
• ISSN: 1012-2443; 1573-7470
• DOI: 10.1007/s10472-021-09736-4

Modeling a combinatorial problem is a hard and error-prone task requiring significant expertise. Constraint acquisition methods attempt to automate this process by learning constraints from examples of solutions and (usually) non-solutions. Active methods query an oracle while passive methods do not. We propose a known but not widely-used application of machine learning to constraint acquisition: training a classifier to discriminate between solutions and non-solutions, then deriving a constraint model from the trained classifier. We discuss a wide range of possible new acquisition methods with useful properties inherited from classifiers. We also show the potential of this approach using a Naive Bayes classifier, obtaining a new passive acquisition algorithm that is considerably faster than existing methods, scalable to large constraint sets, and robust under errors.