BIR: A Method for Selecting the Best Interpretable Multidimensional Scaling Rotation using External Variables

Rebecca Marion, Adrien Bibal, Benoît Frenay

Résultats de recherche: Contribution à un journal/une revueArticle

1 Téléchargements (Pure)

Résumé

Interpreting nonlinear dimensionality reduction models using external features (or external variables) is crucial in many fields, such as psychology and ecology. Multidimensional scaling (MDS) is one of the most frequently used dimensionality reduction techniques in these fields. However, the rotation invariance of the MDS objective function may make interpretation of the resulting embedding difficult. This paper analyzes how the rotation of MDS embeddings affects sparse regression models used to interpret them and proposes a method, called the Best Interpretable Rotation (BIR) method, which selects the best MDS rotation for interpreting embeddings using external information.
langue originaleAnglais
Pages (de - à)83-96
Nombre de pages14
journalNeurocomputing
Volume342
Les DOIs
Etat de la publicationPublié - 4 févr. 2019

Empreinte digitale Examiner les sujets de recherche de « BIR: A Method for Selecting the Best Interpretable Multidimensional Scaling Rotation using External Variables ». Ensemble, ils forment une empreinte digitale unique.

  • Contient cette citation