Lattice-based biclustering using Partition Pattern Structures - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Lattice-based biclustering using Partition Pattern Structures

Victor Codocedo
Amedeo Napoli

Résumé

In this work we present a novel technique for exhaustive bicluster enumeration using formal concept anal-ysis (FCA). Particularly, we use pattern structures (an ex-tension of FCA dealing with complex data) to mine similar row/column biclusters, a specialization of biclustering when attribute values have coherent variations. We show how bi-clustering can benefit from the FCA framework through its ro-bust theoretical description and efficient algorithms. Finally, we evaluate our bicluster mining approach w.r.t. a standard biclustering technique showing very good results in terms of bicluster quality and performance.
Fichier principal
Vignette du fichier
ecai2014.pdf (385.2 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01095865 , version 1 (16-12-2014)

Identifiants

Citer

Victor Codocedo, Amedeo Napoli. Lattice-based biclustering using Partition Pattern Structures. ECAI 2014 - 21st European Conference on Artificial Intelligence, 18-22 August 2014, Prague, Czech Republic - Including Prestigious Applications of Intelligent Systems (PAIS) 2014, Aug 2014, Prague, Czech Republic. ⟨10.3233/978-1-61499-419-0-213⟩. ⟨hal-01095865⟩
182 Consultations
287 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More