TY - JOUR
T1 - An overview of machine learning techniques in constraint solving
AU - Popescu, Andrei
AU - Polat Erdeniz, Seda
AU - Felfernig, Alexander
AU - Uta, Mathias
AU - Atas, Müslüm
AU - Le, Viet Man
AU - Pilsl, Klaus
AU - Enzelsberger, Martin
AU - Tran, Trang
PY - 2022/2
Y1 - 2022/2
N2 - Constraint solving is applied in different application contexts. Examples thereof are the configuration of complex products and services, the determination of production schedules, and the determination of recommendations in online sales scenarios. Constraint solvers apply, for example, search heuristics to assure adequate runtime performance and prediction quality. Several approaches have already been developed showing that machine learning (ML) can be used to optimize search processes in constraint solving. In this article, we provide an overview of the state of the art in applying ML approaches to constraint solving problems including constraint satisfaction, SAT solving, answer set programming (ASP) and applications thereof such as configuration, constraint-based recommendation, and model-based diagnosis. We compare and discuss the advantages and disadvantages of these approaches and point out relevant directions for future work.
AB - Constraint solving is applied in different application contexts. Examples thereof are the configuration of complex products and services, the determination of production schedules, and the determination of recommendations in online sales scenarios. Constraint solvers apply, for example, search heuristics to assure adequate runtime performance and prediction quality. Several approaches have already been developed showing that machine learning (ML) can be used to optimize search processes in constraint solving. In this article, we provide an overview of the state of the art in applying ML approaches to constraint solving problems including constraint satisfaction, SAT solving, answer set programming (ASP) and applications thereof such as configuration, constraint-based recommendation, and model-based diagnosis. We compare and discuss the advantages and disadvantages of these approaches and point out relevant directions for future work.
KW - Answer set programming
KW - Applications
KW - Boolean satisfiability
KW - Constraint satisfaction
KW - Constraint solving
KW - Machine learning
UR - http://dx.doi.org/10.1007/s10844-021-00666-5
UR - http://www.scopus.com/inward/record.url?scp=85113849851&partnerID=8YFLogxK
U2 - 10.1007/s10844-021-00666-5
DO - 10.1007/s10844-021-00666-5
M3 - Article
SN - 0925-9902
VL - 58
SP - 91
EP - 118
JO - Journal of Intelligent Information Systems
JF - Journal of Intelligent Information Systems
IS - 1
ER -