SmartGD: A GAN-Based Graph Drawing Framework for Diverse Aesthetic Goals

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.