EUVIMEDEUVIMED entdecken
Crossref

Novel split quality measures for stratified multilabel cross validation with application to large and sparse gene ontology datasets

Henri Tiittanen, Liisa Holm, Petri Törönen

Applied Computing and Intelligence · 2022

DOI: 10.3934/aci.2022003 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Computing and Intelligence, 2022. Verfasst von Henri Tiittanen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 16 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multilabel learning is an important topic in machine learning research. Evaluating models in multilabel settings requires specific cross validation methods designed for multilabel data. In this article, we show that the most widely used cross validation split quality measure does not behave adequately with multilabel data that has strong class imbalance. We present improved measures and an algorithm, optisplit, for optimizing cross validations splits. Extensive comparison of various types of cross validation methods shows that optisplit produces more even cross validation splits than the existing methods and it is among the fastest methods with good splitting performance.

Zitieren

APA

Tiittanen, H., Holm, L., & Törönen, P. (2022). Novel split quality measures for stratified multilabel cross validation with application to large and sparse gene ontology datasets. Applied Computing and Intelligence. https://doi.org/10.3934/aci.2022003

Vancouver

Tiittanen H, Holm L, Törönen P. Novel split quality measures for stratified multilabel cross validation with application to large and sparse gene ontology datasets. Applied Computing and Intelligence. 2022. doi:10.3934/aci.2022003

BibTeX
@article{Tiittanen2022,
  author = {Tiittanen, Henri and Holm, Liisa and Törönen, Petri},
  title = {Novel split quality measures for stratified multilabel cross validation with application to large and sparse gene ontology datasets},
  journal = {Applied Computing and Intelligence},
  year = {2022},
  doi = {10.3934/aci.2022003}
}
Kostenlos starten →