Visualizing Time-Dependent Data Using Dynamic t-SNE

Rauber, Paulo E.; Falcão, Alexandre X.; Telea, Alexandru C.

Visualizing Time-Dependent Data Using Dynamic t-SNE

Files

073-077.pdf (2.01 MB)

short-0146-file1.zip (16.08 MB)

Date

2016

Authors

Rauber, Paulo E.
Falcão, Alexandre X.
Telea, Alexandru C.

Publisher

The Eurographics Association

Abstract

Many interesting processes can be represented as time-dependent datasets. We define a time-dependent dataset as a sequence of datasets captured at particular time steps. In such a sequence, each dataset is composed of observations (high-dimensional real vectors), and each observation has a corresponding observation across time steps. Dimensionality reduction provides a scalable alternative to create visualizations (projections) that enable insight into the structure of such datasets. However, applying dimensionality reduction independently for each dataset in a sequence may introduce unnecessary variability in the resulting sequence of projections, which makes tracking the evolution of the data significantly more challenging. We show that this issue affects t-SNE, a widely used dimensionality reduction technique. In this context, we propose dynamic t-SNE, an adaptation of t-SNE that introduces a controllable trade-off between temporal coherence and projection reliability. Our evaluation in two time-dependent datasets shows that dynamic t-SNE eliminates unnecessary temporal variability and encourages smooth changes between projections.

        @inproceedings{10.2312:eurovisshort.20161164
,
booktitle = {EuroVis 2016 - Short Papers
},
editor = {Enrico Bertini and Niklas Elmqvist and Thomas Wischgoll
},
title = {{Visualizing Time-Dependent Data Using Dynamic t-SNE
}},
author = {Rauber, Paulo E. and 
Falcão, Alexandre X. and 
Telea, Alexandru C.
},
year = {2016
},
publisher = {The Eurographics Association
},
ISSN = {-
},
ISBN = {978-3-03868-014-7
},
DOI = {10.2312/eurovisshort.20161164
}
}