Graph Neural Networks for Graph Drawing

Tiezzi, Matteo; Ciravegna, Gabriele; Gori, Marco

doi:10.1109/tnnls.2022.3184967

Cited by 10 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other structures, such as Graph Attention Networks (GAT) [34] and Graph Isomorphism Network (GIN) [31], were also proposed to learn from graph data and overcome some of GCNs drawbacks. Tiezzi et al [35] compared the performance of three Shallow Neural Networks (one for GCN, GAT and GIN). They conclude that GAT is the best performing structure out of the three.…”

Section: Learning For Graph Processingmentioning

confidence: 99%

“…But recently, they began drawing attention in the Graph Drawing community. For instance, Tiezzi et al [35] compared GCN, GAT and GIN structures on the Graph Drawing task.…”

Section: Learning For Graph Processingmentioning

confidence: 99%

“…GND [35] and GraphTSNE [37] are two frameworks that use Shallow Neural Networks to draw graphs. While each training of GraphTSNE is done on one specific graph (fed to the model as batches of nodes), GND is trained with batches of graphs to generate layouts of any input graph.…”

Section: Learning For Graph Drawingmentioning

confidence: 99%

See 2 more Smart Citations

Toward Efficient Deep Learning for Graph Drawing (DL4GD)

Giovannangeli

Lalanne

Auber

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

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.

show abstract

Section: Learning For Graph Processingmentioning

confidence: 99%

“…But recently, they began drawing attention in the Graph Drawing community. For instance, Tiezzi et al [35] compared GCN, GAT and GIN structures on the Graph Drawing task.…”

Section: Learning For Graph Processingmentioning

confidence: 99%

See 1 more Smart Citation

Toward Efficient Deep Learning for Graph Drawing (DL4GD)

Giovannangeli

Lalanne

Auber

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…DeepGD [5] and (DNN) 2 [6] directly generate node placements to satisfy specific metrics with graph neural networks. GND [7] trains a Neural Aesthete to determine the quality of the lay-out. However, all of the existing deep learning methods require the whole structure of each neuron.…”

Section: Introductionmentioning

confidence: 99%

GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout

Yan

Zhao

Yang

2022

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY learns the multi-level graph layout process and can generate graph layouts without iterative calculation. We also propose to use Laplacian positional encoding and a multi-level loss fusion strategy to improve the layout learning. We evaluate the model with a random dataset and a graph drawing dataset and showcase the effectiveness and efficiency of GRAPHULY in graph visualization.

show abstract

Minimizing Cross Intersections in Graph Drawing via Linear Splines

Hussain

Tiezzi

Ciravegna

et al. 2022

Artificial Neural Networks in Pattern Recognition

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

Graph Neural Networks for Graph Drawing

Cited by 10 publications

References 50 publications

Toward Efficient Deep Learning for Graph Drawing (DL4GD)

Toward Efficient Deep Learning for Graph Drawing (DL4GD)

GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout

Minimizing Cross Intersections in Graph Drawing via Linear Splines

Contact Info

Product

Resources

About