Improving Neural Network-based Multidimensional Projections

Mateus Espadoto, Nina S. T. Hirata, Alexandre X. Falcão, Alexandru C. Telea

2020

Abstract

Dimensionality reduction methods are often used to explore multidimensional data in data science and information visualization. Techniques of the SNE-class, such as t-SNE, have become the standard for data exploration due to their good visual cluster separation, but are computationally expensive and don’t have out-of-sample capability by default. Recently, a neural network-based technique was proposed, which adds out-of-sample capability to t-SNE with good results, but with the disavantage of introducing some diffusion of the points in the result. In this paper we evaluate many neural network-tuning strategies to improve the results of this technique. We show that a careful selection of network architecture, loss function and data augmentation strategy can improve results.

Download


Paper Citation


in Harvard Style

Espadoto M., Hirata N., Falcão A. and Telea A. (2020). Improving Neural Network-based Multidimensional Projections. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP; ISBN 978-989-758-402-2, SciTePress, pages 29-41. DOI: 10.5220/0008877200290041


in Bibtex Style

@conference{ivapp20,
author={Mateus Espadoto and Nina S. T. Hirata and Alexandre X. Falcão and Alexandru C. Telea},
title={Improving Neural Network-based Multidimensional Projections},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP},
year={2020},
pages={29-41},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008877200290041},
isbn={978-989-758-402-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 3: IVAPP
TI - Improving Neural Network-based Multidimensional Projections
SN - 978-989-758-402-2
AU - Espadoto M.
AU - Hirata N.
AU - Falcão A.
AU - Telea A.
PY - 2020
SP - 29
EP - 41
DO - 10.5220/0008877200290041
PB - SciTePress