Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach
This work addresses a bottleneck in visualization for researchers and practitioners by enabling quantitative evaluation of graph layouts without coordinate access, though it is incremental as it applies existing deep learning techniques to a new domain.
The paper tackles the problem of evaluating graph layout readability when node and edge coordinates are inaccessible by proposing a deep learning approach that uses graph images directly, achieving results comparable to traditional methods.
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 using a case study and visualizing convolutional layers. This work is a first step towards using deep learning based methods to evaluate images from the visualization field quantitatively.