Graph Layouts by t-SNE

J. F. Kruiger, P. E. Rauber, R. M. Martins, A. Kerren, Stephen G Kobourov, A. C. Telea

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

We propose a new graph layout method based on a modification of the t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction technique. Although t-SNE is one of the best techniques for visualizing high-dimensional data as 2D scatterplots, t-SNE has not been used in the context of classical graph layout. We propose a new graph layout method, tsNET, based on representing a graph with a distance matrix, which together with a modified t-SNE cost function results in desirable layouts. We evaluate our method by a formal comparison with state-of-the-art methods, both visually and via established quality metrics on a comprehensive benchmark, containing real-world and synthetic graphs. As evidenced by the quality metrics and visual inspection, tsNET produces excellent layouts.

Original languageEnglish (US)
Pages (from-to)283-294
Number of pages12
JournalComputer Graphics Forum
Volume36
Issue number3
DOIs
StatePublished - Jun 1 2017

Fingerprint

Cost functions
Inspection

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Kruiger, J. F., Rauber, P. E., Martins, R. M., Kerren, A., Kobourov, S. G., & Telea, A. C. (2017). Graph Layouts by t-SNE. Computer Graphics Forum, 36(3), 283-294. https://doi.org/10.1111/cgf.13187

Graph Layouts by t-SNE. / Kruiger, J. F.; Rauber, P. E.; Martins, R. M.; Kerren, A.; Kobourov, Stephen G; Telea, A. C.

In: Computer Graphics Forum, Vol. 36, No. 3, 01.06.2017, p. 283-294.

Research output: Contribution to journalArticle

Kruiger, JF, Rauber, PE, Martins, RM, Kerren, A, Kobourov, SG & Telea, AC 2017, 'Graph Layouts by t-SNE', Computer Graphics Forum, vol. 36, no. 3, pp. 283-294. https://doi.org/10.1111/cgf.13187
Kruiger JF, Rauber PE, Martins RM, Kerren A, Kobourov SG, Telea AC. Graph Layouts by t-SNE. Computer Graphics Forum. 2017 Jun 1;36(3):283-294. https://doi.org/10.1111/cgf.13187
Kruiger, J. F. ; Rauber, P. E. ; Martins, R. M. ; Kerren, A. ; Kobourov, Stephen G ; Telea, A. C. / Graph Layouts by t-SNE. In: Computer Graphics Forum. 2017 ; Vol. 36, No. 3. pp. 283-294.
@article{47a547b57ede4b009e52451b13c00cf6,
title = "Graph Layouts by t-SNE",
abstract = "We propose a new graph layout method based on a modification of the t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction technique. Although t-SNE is one of the best techniques for visualizing high-dimensional data as 2D scatterplots, t-SNE has not been used in the context of classical graph layout. We propose a new graph layout method, tsNET, based on representing a graph with a distance matrix, which together with a modified t-SNE cost function results in desirable layouts. We evaluate our method by a formal comparison with state-of-the-art methods, both visually and via established quality metrics on a comprehensive benchmark, containing real-world and synthetic graphs. As evidenced by the quality metrics and visual inspection, tsNET produces excellent layouts.",
author = "Kruiger, {J. F.} and Rauber, {P. E.} and Martins, {R. M.} and A. Kerren and Kobourov, {Stephen G} and Telea, {A. C.}",
year = "2017",
month = "6",
day = "1",
doi = "10.1111/cgf.13187",
language = "English (US)",
volume = "36",
pages = "283--294",
journal = "Computer Graphics Forum",
issn = "0167-7055",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - Graph Layouts by t-SNE

AU - Kruiger, J. F.

AU - Rauber, P. E.

AU - Martins, R. M.

AU - Kerren, A.

AU - Kobourov, Stephen G

AU - Telea, A. C.

PY - 2017/6/1

Y1 - 2017/6/1

N2 - We propose a new graph layout method based on a modification of the t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction technique. Although t-SNE is one of the best techniques for visualizing high-dimensional data as 2D scatterplots, t-SNE has not been used in the context of classical graph layout. We propose a new graph layout method, tsNET, based on representing a graph with a distance matrix, which together with a modified t-SNE cost function results in desirable layouts. We evaluate our method by a formal comparison with state-of-the-art methods, both visually and via established quality metrics on a comprehensive benchmark, containing real-world and synthetic graphs. As evidenced by the quality metrics and visual inspection, tsNET produces excellent layouts.

AB - We propose a new graph layout method based on a modification of the t-distributed Stochastic Neighbor Embedding (t-SNE) dimensionality reduction technique. Although t-SNE is one of the best techniques for visualizing high-dimensional data as 2D scatterplots, t-SNE has not been used in the context of classical graph layout. We propose a new graph layout method, tsNET, based on representing a graph with a distance matrix, which together with a modified t-SNE cost function results in desirable layouts. We evaluate our method by a formal comparison with state-of-the-art methods, both visually and via established quality metrics on a comprehensive benchmark, containing real-world and synthetic graphs. As evidenced by the quality metrics and visual inspection, tsNET produces excellent layouts.

UR - http://www.scopus.com/inward/record.url?scp=85022223094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85022223094&partnerID=8YFLogxK

U2 - 10.1111/cgf.13187

DO - 10.1111/cgf.13187

M3 - Article

AN - SCOPUS:85022223094

VL - 36

SP - 283

EP - 294

JO - Computer Graphics Forum

JF - Computer Graphics Forum

SN - 0167-7055

IS - 3

ER -