Graph Neural Networks for Graph Drawing

TL;DR

This paper introduces Graph Neural Drawers, a new framework using GNNs with customizable loss functions for creating aesthetically pleasing graph layouts, guided by neural network-based beauty criteria.

Contribution

It proposes a novel GNN-based framework for graph drawing that incorporates neural network-guided loss functions and positional features, enabling complex and aesthetic graph layouts.

Findings

GNNs can be effectively guided by neural network-derived loss functions.

Positional features enhance GNN performance on unlabelled vertices.

The framework successfully minimizes edge crossings in graph layouts.

Abstract

Graph Drawing techniques have been developed in the last few years with the purpose of producing aesthetically pleasing node-link layouts. Recently, the employment of differentiable loss functions has paved the road to the massive usage of Gradient Descent and related optimization algorithms. In this paper, we propose a novel framework for the development of Graph Neural Drawers (GND), machines that rely on neural computation for constructing efficient and complex maps. GNDs are Graph Neural Networks (GNNs) whose learning process can be driven by any provided loss function, such as the ones commonly employed in Graph Drawing. Moreover, we prove that this mechanism can be guided by loss functions computed by means of Feedforward Neural Networks, on the basis of supervision hints that express beauty properties, like the minimization of crossing edges. In this context, we show that GNNs can nicely be enriched by positional features to deal also with unlabelled vertexes. We provide a proof-of-concept by constructing a loss function for the edge-crossing and provide quantitative and qualitative comparisons among different GNN models working under the proposed framework.