A Deep Generative Model for Graph Layout

Oh Hyun Kwon, Kwan Liu Ma

Research output: Contribution to journalArticle

Abstract

Different layouts can characterize different aspects of the same graph. Finding a 'good' layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-And-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.

Original languageEnglish (US)
Article number8805452
Pages (from-to)665-675
Number of pages11
JournalIEEE Transactions on Visualization and Computer Graphics
Volume26
Issue number1
DOIs
StatePublished - Jan 2020

Fingerprint

Visualization
Learning systems

Keywords

  • autoencoder
  • deep learning
  • generative model
  • Graph
  • layout
  • machine learning
  • network
  • neural network
  • visualization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

A Deep Generative Model for Graph Layout. / Kwon, Oh Hyun; Ma, Kwan Liu.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 26, No. 1, 8805452, 01.2020, p. 665-675.

Research output: Contribution to journalArticle

@article{9c0831eb902f4cb998b9d9561a8d90f0,
title = "A Deep Generative Model for Graph Layout",
abstract = "Different layouts can characterize different aspects of the same graph. Finding a 'good' layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-And-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.",
keywords = "autoencoder, deep learning, generative model, Graph, layout, machine learning, network, neural network, visualization",
author = "Kwon, {Oh Hyun} and Ma, {Kwan Liu}",
year = "2020",
month = "1",
doi = "10.1109/TVCG.2019.2934396",
language = "English (US)",
volume = "26",
pages = "665--675",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "1",

}

TY - JOUR

T1 - A Deep Generative Model for Graph Layout

AU - Kwon, Oh Hyun

AU - Ma, Kwan Liu

PY - 2020/1

Y1 - 2020/1

N2 - Different layouts can characterize different aspects of the same graph. Finding a 'good' layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-And-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.

AB - Different layouts can characterize different aspects of the same graph. Finding a 'good' layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-And-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.

KW - autoencoder

KW - deep learning

KW - generative model

KW - Graph

KW - layout

KW - machine learning

KW - network

KW - neural network

KW - visualization

UR - http://www.scopus.com/inward/record.url?scp=85075636320&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85075636320&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2019.2934396

DO - 10.1109/TVCG.2019.2934396

M3 - Article

C2 - 31425108

AN - SCOPUS:85075636320

VL - 26

SP - 665

EP - 675

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 1

M1 - 8805452

ER -