Comparaison de différents modèles de programmation par contraintes pour le clustering conceptuel

Maxime Chabert Pierre-Antoine Champin 1 Amélie Cordier 2 Christine Solnon 3
1 TWEAK - Traces, Web, Education, Adaptation, Knowledge
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 SMA - Systèmes Multi-Agents
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
3 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Conceptual clustering allows to partition a set of objects into clusters of similar objects, corresponding to formal concepts. We present a new approach based on constraint programming where formal concepts are extracted in a pre-processing step by using a dedicated data-mining approach. We compare the efficiency of our approach with several recent approaches using constraint programming or integer linear programming on classical machine learning instances. We also introduce a new set of instances coming from a real application case, which aims at extracting setting concepts from an Enterprise Ressource Planning (ERP) software. We assess the relevance of extracted concepts depending on criteria used in the objective function.
Document type :
Conference papers
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02076396
Contributor : Pierre-Antoine Champin <>
Submitted on : Friday, March 22, 2019 - 10:08:12 AM
Last modification on : Tuesday, June 25, 2019 - 4:11:33 PM
Long-term archiving on : Sunday, June 23, 2019 - 1:38:34 PM

File

JFPC_2017_paper_13.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02076396, version 1

Citation

Maxime Chabert, Pierre-Antoine Champin, Amélie Cordier, Christine Solnon. Comparaison de différents modèles de programmation par contraintes pour le clustering conceptuel. Treizièmes journées Francophones de Programmation par Contraintes, Jun 2017, Montreuil sur Mer, France. ⟨hal-02076396⟩

Share

Metrics

Record views

33

Files downloads

32