Cross-View kernel transfer - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2022

Cross-View kernel transfer

Résumé

We consider the kernel completion problem with the presence of multiple views in the data. In this context the data samples can be fully missing in some views, creating missing columns and rows to the kernel matrices that are calculated individually for each view. We propose to solve the problem of completing the kernel matrices with Cross-View Kernel Transfer (CVKT) procedure, in which the features of the other views are transformed to represent the view under consideration. The transformations are learned with kernel alignment to the known part of the kernel matrix, allowing for finding generalizable structures in the kernel matrix under completion. Its missing values can then be predicted with the data available in other views. We illustrate the benefits of our approach with simulated data, multivariate digits dataset and multi-view dataset on gesture classification, as well as with real biological datasets from studies of pattern formation in early Drosophila melanogaster embryogenesis.
Fichier principal
Vignette du fichier
1-s2.0-S0031320322002400-main.pdf (3.74 Mo) Télécharger le fichier
Origine : Publication financée par une institution

Dates et versions

hal-03845345 , version 1 (09-11-2022)

Identifiants

Citer

Riikka Huusari, Cécile Capponi, Paul Villoutreix, Hachem Kadri. Cross-View kernel transfer. Pattern Recognition, 2022, 129, pp.108759. ⟨10.1016/j.patcog.2022.108759⟩. ⟨hal-03845345⟩
13 Consultations
14 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More