Deep Neural Network for DrawiNg Networks, $${(DNN)^{\textit{2}\,}} $$

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