Deep Neural Network for DrawiNg Networks, (DNN)^2

Abstract

By leveraging recent progress of stochastic gradient descent methods, several works have shown that graphs could be efficiently laid out through the optimization of a tailored objective function. In the meantime, Deep Learning (DL) techniques achieved great performances in many applications. We demonstrate that it is possible to use DL techniques to learn a graph-to-layout sequence of operations thanks to a graph-related objective function. In this paper, we present a novel graph drawing framework called (DNN)^2: Deep Neural Network for DrawiNg Networks. Our method uses Graph Convolution Networks to learn a model. Learning is achieved by optimizing a graph topology related loss function that evaluates (DNN)^2 generated layouts during training. Once trained, the (DNN)^ model is able to quickly lay any input graph out. We experiment (DNN)^2 and statistically compare it to optimization-based and regular graph layout algorithms. The results show that (DNN)^2 performs well and are encouraging as the Deep Learning approach to Graph Drawing is novel and many leads for future works are identified.

arXiv commentAppears in the Proceedings of the 29th International Symposium on Graph Drawing and Network Visualization (GD 2021)

References in corpus (7)

• Semi-Supervised Classification with Graph Convolutional Networks
• What Would a Graph Look Like in This Layout? A Machine Learning Approach to Large Graph Visualization
• A Deep Generative Model for Graph Layout
• Evaluating the Readability of Force Directed Graph Layouts: A Deep Learning Approach
• Toward automatic comparison of visualization techniques: Application to graph visualization
• GraphTSNE: A Visualization Technique for Graph-Structured Data
• Graph Drawing via Gradient Descent, $(GD{)}^2$