Evaluating the readability of force directed graph layouts: A deep learning approach

Existing graph layout algorithms are usually not able to optimize all the aesthetic properties desired in a graph layout. To evaluate how well the desired visual features are reflected in a graph layout, many readability metrics have been proposed in the past decades. However, the calculation of the...

Full description

Saved in:
Bibliographic Details
Main Authors: HALEEM, Hammad, WANG, Yong, PURI, Abishek, WADHWA, Sahil, QU, Huamin
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2019
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/5375
https://ink.library.smu.edu.sg/context/sis_research/article/6379/viewcontent/evaluating__PV.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-6379
record_format dspace
spelling sg-smu-ink.sis_research-63792020-12-02T04:44:39Z Evaluating the readability of force directed graph layouts: A deep learning approach HALEEM, Hammad WANG, Yong PURI, Abishek WADHWA, Sahil QU, Huamin Existing graph layout algorithms are usually not able to optimize all the aesthetic properties desired in a graph layout. To evaluate how well the desired visual features are reflected in a graph layout, many readability metrics have been proposed in the past decades. However, the calculation of these readability metrics often requires access to the node and edge coordinates and is usually computationally inefficient, especially for dense graphs. Importantly, when the node and edge coordinates are not accessible, it becomes impossible to evaluate the graph layouts quantitatively. In this paper, we present a novel deep learning-based approach to evaluate the readability of graph layouts by directly using graph images. A convolutional neural network architecture is proposed and trained on a benchmark dataset of graph images, which is composed of synthetically-generated graphs and graphs created by sampling from real large networks. Multiple representative readability metrics (including edge crossing, node spread, and group overlap) are considered in the proposed approach. We quantitatively compare our approach to traditional methods and qualitatively evaluate our approach by showing usage scenarios and visualizing convolutional layers. This work is a first step towards using deep learning based methods to quantitatively evaluate images from the visualization field. 2019-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5375 info:doi/10.1109/MCG.2018.2881501 https://ink.library.smu.edu.sg/context/sis_research/article/6379/viewcontent/evaluating__PV.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graphics and Human Computer Interfaces Software Engineering
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Graphics and Human Computer Interfaces
Software Engineering
spellingShingle Graphics and Human Computer Interfaces
Software Engineering
HALEEM, Hammad
WANG, Yong
PURI, Abishek
WADHWA, Sahil
QU, Huamin
Evaluating the readability of force directed graph layouts: A deep learning approach
description Existing graph layout algorithms are usually not able to optimize all the aesthetic properties desired in a graph layout. To evaluate how well the desired visual features are reflected in a graph layout, many readability metrics have been proposed in the past decades. However, the calculation of these readability metrics often requires access to the node and edge coordinates and is usually computationally inefficient, especially for dense graphs. Importantly, when the node and edge coordinates are not accessible, it becomes impossible to evaluate the graph layouts quantitatively. In this paper, we present a novel deep learning-based approach to evaluate the readability of graph layouts by directly using graph images. A convolutional neural network architecture is proposed and trained on a benchmark dataset of graph images, which is composed of synthetically-generated graphs and graphs created by sampling from real large networks. Multiple representative readability metrics (including edge crossing, node spread, and group overlap) are considered in the proposed approach. We quantitatively compare our approach to traditional methods and qualitatively evaluate our approach by showing usage scenarios and visualizing convolutional layers. This work is a first step towards using deep learning based methods to quantitatively evaluate images from the visualization field.
format text
author HALEEM, Hammad
WANG, Yong
PURI, Abishek
WADHWA, Sahil
QU, Huamin
author_facet HALEEM, Hammad
WANG, Yong
PURI, Abishek
WADHWA, Sahil
QU, Huamin
author_sort HALEEM, Hammad
title Evaluating the readability of force directed graph layouts: A deep learning approach
title_short Evaluating the readability of force directed graph layouts: A deep learning approach
title_full Evaluating the readability of force directed graph layouts: A deep learning approach
title_fullStr Evaluating the readability of force directed graph layouts: A deep learning approach
title_full_unstemmed Evaluating the readability of force directed graph layouts: A deep learning approach
title_sort evaluating the readability of force directed graph layouts: a deep learning approach
publisher Institutional Knowledge at Singapore Management University
publishDate 2019
url https://ink.library.smu.edu.sg/sis_research/5375
https://ink.library.smu.edu.sg/context/sis_research/article/6379/viewcontent/evaluating__PV.pdf
_version_ 1770575436871368704