Mixture of von Mises-Fisher distribution with sparse prototypes - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Neurocomputing Année : 2022

Mixture of von Mises-Fisher distribution with sparse prototypes

Résumé

Mixtures of von Mises-Fisher distributions can be used to cluster data on the unit hypersphere. This is particularly adapted for high-dimensional directional data such as texts. We propose in this article to estimate a von Mises mixture using a l 1 penalized likelihood. This leads to sparse prototypes that improve clustering interpretability. We introduce an expectation-maximisation (EM) algorithm for this estimation and explore the trade-off between the sparsity term and the likelihood one with a path following algorithm. The model's behaviour is studied on simulated data and, we show the advantages of the approach on real data benchmark. We also introduce a new data set on financial reports and exhibit the benefits of our method for exploratory analysis.
Fichier principal
Vignette du fichier
neuro_template.pdf (941.56 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03909654 , version 1 (22-12-2022)

Licence

Identifiants

Citer

Fabrice Rossi, Florian Barbaro. Mixture of von Mises-Fisher distribution with sparse prototypes. Neurocomputing, 2022, 501, pp.41-74. ⟨10.1016/j.neucom.2022.05.118⟩. ⟨hal-03909654⟩
55 Consultations
189 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More