GraphTSNE: A Visualization Technique for Graph-Structured Data
This work addresses the need for human insight into graph data, offering a visualization technique that combines structural and feature information, though it is incremental as it builds on existing t-SNE and graph methods.
The authors tackled the problem of visualizing graph-structured data by developing GraphTSNE, a method that integrates both graph structure and node features, and demonstrated its effectiveness on three benchmark datasets.
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. 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 the graph structure. On the other hand, visualization techniques which operate on graphs, such as Laplacian Eigenmaps and tsNET, have no mechanism to make use of information from node features. Our proposed method GraphTSNE produces visualizations which account for both graph structure 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.