Toward Efficient Deep Learning for Graph Drawing (DL4GD)

Abstract

Due to their great performance in many challenges, Deep Learning (DL) techniques keep gaining popularity in many fields. They have been adapted to process graph data structures to solve various complicated tasks such as graph classification and edge prediction. Eventually, they reached the Graph Drawing (GD) task. This paper is an extended version of the previously published (DNN) 2 and presents a framework to leverage DL techniques for graph drawing (DL4GD). We demonstrate how it is possible to train a Deep Learning model to extract features from a graph and project them into a graph layout. The method proposes to leverage efficient Convolutional Neural Networks, adapting them to graphs using Graph Convolutions. The graph layout projection is learned by optimizing a cost function that does not require any ground truth layout, as opposed to prior work. This paper also proposes an implementation and benchmark of the framework to study its sensitivity to certain deep learning-related conditions. As the field is novel, and many questions remain to be answered, we do not focus on finding the most optimal implementation of the method, but rather contribute toward a better understanding of the approach potential. More precisely, we study different learning strategies relative to the models training datasets. Finally, we discuss the main advantages and limitations of DL4GD.

Graphs Drawn With Some Vertices per Face: Density and Relationships

“…Also, the charge ch ′ (f ) is decreased by at most (d − 3) 2 3 . Since the excess of f before the operation was equal to d − 10 3 , the new excess after the operation is at least d − 10 3 −(d −3) 2 3 = 1 3 d − 4 3 , which is always non-negative for d ≥ 4. Hence, ch ′ (f ) still satisfies C1.…”

“…Examples of these domains include social sciences, software engineering, biology, finance, and computer networks (see, e.g., [5], [6], [7], [8], [9]). The importance of graph visualization has also been highlighted in the contexts of machine learning, knowledge discovery, and explainable AI, which further characterizes the interdisciplinary nature of this research area (see, e.g., [10], [11], [12], [13]).…”