GraphTSNE: A Visualization Technique for Graph-Structured Data

by   Yao Yang Leow, et al.

We present GraphTSNE, a novel visualization technique for graph-structured data based on t-SNE. The growing interest in graph-structured data increases the importance of gaining human insight into such datasets by means of visualization. However, among the most popular visualization techniques, classical t-SNE is not suitable on such datasets because it has no mechanism to make use of information from graph connectivity. On the other hand, standard graph visualization techniques, such as Laplacian Eigenmaps, have no mechanism to make use of information from node features. Our proposed method GraphTSNE is able to produce visualizations which account for both graph connectivity and node features. It is based on scalable and unsupervised training of a graph convolutional network on a modified t-SNE loss. By assembling a suite of evaluation metrics, we demonstrate that our method produces desirable visualizations on three benchmark datasets.


What is Data Visualization and Why Is It Important?

#Datavisualization is the act of taking information (data) and placing i...

Graffinity: Visualizing Connectivity In Large Graphs

Multivariate graphs are prolific across many fields, including transport...

Gaining insight into SARS-CoV-2 infection and COVID-19 severity using self-supervised edge features and Graph Neural Networks

Graph Neural Networks (GNN) have been extensively used to extract meanin...

Manifold learning for brain connectivity

Human brain connectome studies aim at extracting and analyzing relevant ...

Exploring the Design Space of Aesthetics with the Repertory Grid Technique

By optimizing aesthetics, graph diagrams can be generated that are easie...

Spectral Visualization Sharpening

In this paper, we propose a perceptually-guided visualization sharpening...

Vectorizing Quantum Turbulence Vortex-Core Lines for Real-Time Visualization

Vectorizing vortex-core lines is crucial for high-quality visualization ...

Code Repositories


PyTorch Implementation of GraphTSNE, ICLR’19

view repo