ParaDime: A Framework for Parametric Dimensionality Reduction

ParaDime Teaser

Abstract

ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface to specify the way these relations and transformations are computed and how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. Furthermore, it allows users to fully customize each aspect of the DR process. We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques, such as hybrid classification/embedding models or supervised DR, which opens up new possibilities for visualizing high-dimensional data.


Citation

Andreas Hinterreiter, Christina Humer, Bernhard Kainz, Marc Streit
ParaDime: A Framework for Parametric Dimensionality Reduction
arXiv:2210.04582 [cs.LG], doi:10.48550/arXiv.2210.04582, 2022.

BibTeX

@article{,
    title = {ParaDime: A Framework for Parametric Dimensionality Reduction},
    author = {Andreas Hinterreiter and Christina Humer and Bernhard Kainz and Marc Streit},
    journal = {arXiv:2210.04582 [cs.LG]},
    doi = {10.48550/arXiv.2210.04582},
    url = {https://arxiv.org/abs/2210.04582},
    month = {October},
    year = {2022}
}