Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/77030
Title: GraphTSNE : a visualization technique for graph-structured data
Authors: Leow, Yao Yang
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2019
Abstract: 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. Our proposed method GraphTSNE is able to produce visualizations which account for both graph connectivity and node features. It is based on unsupervised training of a graph convolutional network on a modified tSNE loss. The network is trained in a scalable fashion and can be used inductively to project unseen data points. By assembling a suite of evaluation metrics, we demonstrate that our method outperforms existing visualization techniques on graph datasets and produces desirable visualizations on benchmark datasets.
URI: http://hdl.handle.net/10356/77030
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
report.pdf
  Restricted Access
6.9 MBAdobe PDFView/Open

Page view(s)

90
Updated on May 6, 2021

Download(s)

14
Updated on May 6, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.