Cross-view kernel transfer

Riikka Huusari*, Cécile Capponi, Paul Villoutreix, Hachem Kadri

*Corresponding author for this work

Research output: Contribution to journalArticleScientificpeer-review

33 Downloads (Pure)

Abstract

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.

Original languageEnglish
Article number108759
Pages (from-to)1-14
Number of pages14
JournalPattern Recognition
Volume129
DOIs
Publication statusPublished - Sept 2022
MoE publication typeA1 Journal article-refereed

Keywords

  • Cross-view transfer
  • Kernel completion
  • Kernel learning
  • Multi-view learning

Fingerprint

Dive into the research topics of 'Cross-view kernel transfer'. Together they form a unique fingerprint.

Cite this