DeepFD: a deep learning approach to fast generate force-directed layout for large graphs

IF 1.7 4区计算机科学 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Journal of Visualization Pub Date : 2024-05-31 DOI:10.1007/s12650-024-00991-1

Shuhang Zhang, Ruihong Xu, Qing Zhang, Yining Quan, Qi Liu

{"title":"DeepFD: a deep learning approach to fast generate force-directed layout for large graphs","authors":"Shuhang Zhang, Ruihong Xu, Qing Zhang, Yining Quan, Qi Liu","doi":"10.1007/s12650-024-00991-1","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Deep learning techniques have been applied to the graph drawing of node-link diagrams to help figure out user preference of layout in recent research. However, when revisiting existing studies, only stress model and dimensional reduction methods are utilized in the unsupervised learning of graph drawing tasks since their gradient descent conditions can be easily constructed, and few works have explored their scalability on large graphs. In this paper, we propose a framework that can adapt most of the graph layout methods to a form of loss function and develop an implementation DeepFD, which takes the force-directed algorithm as the prototype to design the loss function. Our model is built with the graph-LSTM as encoder and multilayer perceptron as decoder and trained with dataset split from huge graphs with millions of nodes by Louvain. We design a set of qualitative and quantitative experiments to evaluate our method and compare with classical layout techniques such as F-R and K-K algorithms, while deep-learning based models with various architecture or loss function are adopted to perform ablation experiments. The results indicate that our developed approach can generate a high-quality layout of large graph within a low time cost, and the model we propose shows strong robustness and high efficiency.</p><h3 data-test=\"abstract-sub-heading\">Graphical abstract</h3>","PeriodicalId":54756,"journal":{"name":"Journal of Visualization","volume":"22 7 1","pages":""},"PeriodicalIF":1.7000,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Visualization","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s12650-024-00991-1","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}

引用次数: 0

Abstract

Deep learning techniques have been applied to the graph drawing of node-link diagrams to help figure out user preference of layout in recent research. However, when revisiting existing studies, only stress model and dimensional reduction methods are utilized in the unsupervised learning of graph drawing tasks since their gradient descent conditions can be easily constructed, and few works have explored their scalability on large graphs. In this paper, we propose a framework that can adapt most of the graph layout methods to a form of loss function and develop an implementation DeepFD, which takes the force-directed algorithm as the prototype to design the loss function. Our model is built with the graph-LSTM as encoder and multilayer perceptron as decoder and trained with dataset split from huge graphs with millions of nodes by Louvain. We design a set of qualitative and quantitative experiments to evaluate our method and compare with classical layout techniques such as F-R and K-K algorithms, while deep-learning based models with various architecture or loss function are adopted to perform ablation experiments. The results indicate that our developed approach can generate a high-quality layout of large graph within a low time cost, and the model we propose shows strong robustness and high efficiency.

Graphical abstract

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

DeepFD：为大型图形快速生成力导向布局的深度学习方法

摘要在最近的研究中，深度学习技术被应用于节点链接图的绘制，以帮助找出用户对布局的偏好。然而，回顾现有研究，只有应力模型和降维方法被用于图绘制任务的无监督学习，因为它们的梯度下降条件很容易构建，而且很少有研究探讨它们在大型图上的可扩展性。在本文中，我们提出了一个框架，可以将大多数图绘制方法调整为一种损失函数形式，并开发了一种以力导向算法为原型设计损失函数的实现 DeepFD。我们的模型以图-LSTM 作为编码器，以多层感知器作为解码器，并使用卢万从具有数百万节点的巨大图中分离出来的数据集进行训练。我们设计了一系列定性和定量实验来评估我们的方法，并与经典的布局技术（如 F-R 和 K-K 算法）进行比较，同时采用基于深度学习的模型和各种架构或损失函数来执行消融实验。结果表明，我们开发的方法可以在较低的时间成本内生成高质量的大型图布局，而且我们提出的模型表现出很强的鲁棒性和很高的效率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Journal of Visualization COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY

CiteScore

3.40

自引率

5.90%

发文量

审稿时长

>12 weeks

期刊介绍： Visualization is an interdisciplinary imaging science devoted to making the invisible visible through the techniques of experimental visualization and computer-aided visualization. The scope of the Journal is to provide a place to exchange information on the latest visualization technology and its application by the presentation of latest papers of both researchers and technicians.