arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.09477cs.HCcs.LG
收藏

可视化技术的自动比较:应用于图形可视化

Toward automatic comparison of visualization techniques: Application to graph visualization

LaBRI(波尔多计算机研究实验室)

L. Giovannangeli, R. Bourqui, R. Giot, D. Auber

摘要:

在过去的几十年中,许多最终用户对数据可视化技术进行了评估。他们的结果是构建高效可视化系统的基石。然而,设计这样的评价总是复杂和耗时的,并可能导致缺乏统计证据和可重复性。我们相信,现代和高效的计算机视觉技术,如深度卷积神经网络(CNN),可以帮助可视化研究人员建立和/或调整他们的评估假设。我们的想法的基础是在几种可视化技术上训练机器学习模型来解决特定的任务。我们的假设是,它是可以比较的可视化技术的基础上,其相应的模型的性能的效率。由于当前的机器学习模型无法严格反映人类的能力,包括其不完善之处,因此应谨慎解释此类结果。然而,我们认为使用基于机器学习的预评估,作为标准用户评估的预处理,应该有助于研究人员对其设计空间进行更详尽的研究。因此,它应该通过提供更好的测试用例来提高最终用户的评估。在本文中,我们提出了两个实验的结果,我们已经进行了评估如何相关的用户和计算机视觉技术的性能可以。该研究比较了两种主流的图形可视化技术:节点链接(\NL)和邻接矩阵(\MD)图。使用两个著名的深度卷积神经网络,我们部分复制了Ghoniem \textit{et al.}和Okoe \textit{et al.}的用户评价。实验结果表明,部分用户评价结果可以自动再现。

英文摘要:

Many end-user evaluations of data visualization techniques have been run during the last decades. Their results are cornerstones to build efficient visualization systems. However, designing such an evaluation is always complex and time-consuming and may end in a lack of statistical evidence and reproducibility. We believe that modern and efficient computer vision techniques, such as deep convolutional neural networks (CNNs), may help visualization researchers to build and/or adjust their evaluation hypothesis. The basis of our idea is to train machine learning models on several visualization techniques to solve a specific task. Our assumption is that it is possible to compare the efficiency of visualization techniques based on the performance of their corresponding model. As current machine learning models are not able to strictly reflect human capabilities, including their imperfections, such results should be interpreted with caution. However, we think that using machine learning-based pre-evaluation, as a pre-process of standard user evaluations, should help researchers to perform a more exhaustive study of their design space. Thus, it should improve their final user evaluation by providing it better test cases. In this paper, we present the results of two experiments we have conducted to assess how correlated the performance of users and computer vision techniques can be. That study compares two mainstream graph visualization techniques: node-link (\NL) and adjacency-matrix (\MD) diagrams. Using two well-known deep convolutional neural networks, we partially reproduced user evaluations from Ghoniem \textit{et al.} and from Okoe \textit{et al.}. These experiments showed that some user evaluation results can be reproduced automatically.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑