New Approaches to Constraint Acquisition

Christian Bessiere (1) , Abderrazak Daoudi (1, 2) , Emmanuel Hébrard , George Katsirelos (3) , Nadjib Lazaar (1) , Younes Mechqrane (2) , Nina Narodytska (4) , Claude-Guy Quimper (5) , Toby Walsh (6)

1 COCONUT - Agents, Apprentissage, Contraintes
2 UM5 - Université Mohammed V de Rabat [Agdal]
3 MIAT INRA - Unité de Mathématiques et Informatique Appliquées de Toulouse
4 Samsung Research America [San José]
5 ULaval - Université Laval [Québec]
6 NICTA - National ICT Australia [Sydney]

In this chapter we present the recent results on constraint acquisition obtained by the Coconut team and their collaborators. In a first part we show how to learn constraint networks by asking the user partial queries. That is, we ask the user to classify assignments to subsets of the variables as positive or negative. We provide an algorithm, called QUACQ, that, given a negative example, finds a constraint of the target network in a number of queries logarithmic in the size of the example. In a second part, we show that using some background knowledge may improve the acquisition process a lot. We introduce the concept of generalization query based on an aggregation of variables into types. We propose a generalization algorithm together with several strategies that we incorporate in QUACQ. Finally we evaluate our algorithms on some benchmarks.

Domaines: Sciences du Vivant [q-bio]

Christian Bessiere, Abderrazak Daoudi, Emmanuel Hébrard, George Katsirelos, Nadjib Lazaar, et al.. New Approaches to Constraint Acquisition. Data Mining and Constraint Programming, 10101 (Chapter 3), Springer International Publishing AG, pp.51-76, 2016, Lecture Notes in Computer Science, 978-3-319-50136-9. ⟨10.1007/978-3-319-50137-6_3⟩. ⟨hal-01606245⟩