Graph Layouts by t‐SNE

Размещения графов с помощью t-SNE
Stephen Kobourov, Rafael M. Martins, Andreas Kerren, Alexandru Cristian Telea, Paulo Rauber, Johannes F. Kruiger
2017-06-01

dimensionality reductiongraph layoutgraph visualizationt-SNEtsNET
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.
1
Evaluation on a comprehensive benchmark of real-world and synthetic graphs shows that tsNET produces excellent layouts.
2
The method is formally evaluated against state-of-the-art graph layout techniques using visual assessment and established quality metrics.
3
The paper introduces tsNET, a graph layout method based on a modified t-SNE dimensionality-reduction technique.
4
tsNET represents graphs using a distance matrix and modifies the t-SNE cost function to generate graph layouts.

graphs represented by distance matrices

the quality of 2D graph layouts produced by a modified t-SNE method, evaluated visually and with established layout metrics

Publication Details
Publication Date
2017-06-01
Journal
Publisher
ISSN
Cited by
99
Access Type
Author Information
Authors
Stephen Kobourov
Rafael M. Martins
Andreas Kerren
Alexandru Cristian Telea
Paulo Rauber
Johannes F. Kruiger
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%