Aesthetic Discrimination of Graph Layouts

TL;DR

This paper introduces a neural network model that effectively discriminates between graph layouts based on aesthetic quality, leveraging diverse features and a large dataset, achieving high accuracy in aesthetic assessment.

Contribution

The paper presents a novel neural network discriminator trained on a comprehensive dataset, combining multiple known metrics and physics-inspired features for graph aesthetic evaluation.

Findings

Achieves 95.70% accuracy in predicting aesthetic quality.

Outperforms existing stress-based and metric-based discriminators.

Utilizes a diverse feature set including physics-inspired statistics.

Abstract

This paper addresses the following basic question: given two layouts of the same graph, which one is more aesthetically pleasing? We propose a neural network-based discriminator model trained on a labeled dataset that decides which of two layouts has a higher aesthetic quality. The feature vectors used as inputs to the model are based on known graph drawing quality metrics, classical statistics, information-theoretical quantities, and two-point statistics inspired by methods of condensed matter physics. The large corpus of layout pairs used for training and testing is constructed using force-directed drawing algorithms and the layouts that naturally stem from the process of graph generation. It is further extended using data augmentation techniques. The mean prediction accuracy of our model is 95.70%, outperforming discriminators based on stress and on the linear combination of popular quality metrics by a statistically significant margin.