A multitude of studies have been conducted on graph drawing, but many existing methods only focus on optimizing a single aesthetic aspect of graph layouts. There are a few existing methods that attempt to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria. Furthermore, thanks to the significant advance in deep learning techniques, several deep learning-based layout methods were proposed recently, which have demonstrated the advantages of the deep learning approaches for graph drawing. However, none of these existing methods can be directly applied to optimizing non-differentiable criteria without special accommodation. In this work, we propose a novel Generative Adversarial Network (GAN) based deep learning framework for graph drawing, called SmartGD, which can optimize any quantitative aesthetic goals even though they are non-differentiable. In the cases where the aesthetic goal is too abstract to be described mathematically, SmartGD can draw graphs in a similar style as a collection of good layout examples, which might be selected by humans based on the abstract aesthetic goal. To demonstrate the effectiveness and efficiency of SmartGD, we conduct experiments on minimizing stress, minimizing edge crossing, maximizing crossing angle, and a combination of multiple aesthetics. Compared with several popular graph drawing algorithms, the experimental results show that SmartGD achieves good performance both quantitatively and qualitatively.

翻译：对图表绘制进行了多种研究,但许多现有方法仅侧重于优化图形布局的单一审美方面,有一些现有方法试图为优化不同审美方面的不同审美方面制定灵活的解决办法,此外,由于深层次学习技术的显著进步,最近提出了一些深层次的基于学习的布局方法,这些方法展示了绘图的深层次学习方法的优点。然而,这些现有方法没有一个可以直接用于优化非差别性标准,而没有特殊的便利。在这项工作中,我们提议建立一个基于图表绘制的基于新颖的General Aversarial网络(GAN)的深层次学习框架,称为SmartGD,它可以优化任何定量审美目标,尽管它们不具有差异性。在审美目标过于抽象、无法用数学描述的情况下,SmartGD可以绘制类似风格的图表,以抽象的审美目标为人类选择。为了展示SmartGD的有效性和效率,我们进行了关于尽量减少压力、最大限度地减少边缘跨度、优化跨度、优化跨度、优化跨度、优化多层次的定量的定量分析,以及将多种定性的定性分析结果结合起来。