SDR-NNP: Sharpened Dimensionality Reduction with Neural Networks

Youngjoo Kim, Mateus Espadoto, Scott C. Trager, Jos B. T. M. Roerdink, Alexandru C. Telea

2022

Abstract

Dimensionality reduction (DR) methods aim to map high-dimensional datasets to 2D scatterplots for visual exploration. Such scatterplots are used to reason about the cluster structure of the data, so creating well-separated visual clusters from existing data clusters is an important requirement of DR methods. Many DR methods excel in speed, implementation simplicity, ease of use, stability, and out-of-sample capabilities, but produce suboptimal cluster separation. Recently, Sharpened DR (SDR) was proposed to generically help such methods by sharpening the data-distribution prior to the DR step. However, SDR has prohibitive computational costs for large datasets. We present SDR-NNP, a method that uses deep learning to keep the attractive sharpening property of SDR while making it scalable, easy to use, and having the out-of-sample ability. We demonstrate SDR-NNP on seven datasets, applied on three DR methods, using an extensive exploration of its parameter space. Our results show that SDR-NNP consistently produces projections with clear cluster separation, assessed both visually and by four quality metrics, at a fraction of the computational cost of SDR. We show the added value of SDR-NNP in a concrete use-case involving the labeling of astronomical data.

Paper Citation

in Harvard Style

Kim Y., Espadoto M., Trager S., Roerdink J. and Telea A. (2022). SDR-NNP: Sharpened Dimensionality Reduction with Neural Networks. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP; ISBN 978-989-758-555-5, SciTePress, pages 63-76. DOI: 10.5220/0010820900003124

in Bibtex Style

@conference{ivapp22,
author={Youngjoo Kim and Mateus Espadoto and Scott C. Trager and Jos B. T. M. Roerdink and Alexandru C. Telea},
title={SDR-NNP: Sharpened Dimensionality Reduction with Neural Networks},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP},
year={2022},
pages={63-76},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010820900003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 3: IVAPP
TI - SDR-NNP: Sharpened Dimensionality Reduction with Neural Networks
SN - 978-989-758-555-5
AU - Kim Y.
AU - Espadoto M.
AU - Trager S.
AU - Roerdink J.
AU - Telea A.
PY - 2022
SP - 63
EP - 76
DO - 10.5220/0010820900003124
PB - SciTePress