DROPS

Artifact

Software

NNP-NET

Authors: Ilan Hartskeerl, Tamara Mchedlidze, Simon van Wageningen, Peter Vangorp, and Alexandru Telea

Abstract

Cite as

Ilan Hartskeerl, Tamara Mchedlidze, Simon van Wageningen, Peter Vangorp, Alexandru Telea. NNP-NET (Software, Source Code). Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@misc{software_nnpnet,
   title = {{NNP-NET}}, 
   author = {Hartskeerl, Ilan and Mchedlidze, Tamara and van Wageningen, Simon and Vangorp, Peter and Telea, Alexandru},
   note = {Software, swhId: \href{https://archive.softwareheritage.org/swh:1:dir:539da3e3adda73abc8bb1af0c2a5c59fb7abef49;origin=https://github.com/IlanHartskeerl/NNP-NET;visit=swh:1:snp:cc28063a07356e46bb4d2ca85ac1e7098c891196;anchor=swh:1:rev:7baafec7993065930575f63f4697ee575bb05f0a}{\texttt{swh:1:dir:539da3e3adda73abc8bb1af0c2a5c59fb7abef49}} (visited on 2025-11-26)},
   url = {https://github.com/IlanHartskeerl/NNP-NET},
   doi = {10.4230/artifacts.25058},
}

Document

DOI: 10.4230/LIPIcs.GD.2025.22

NNP-NET: Accelerating t-SNE Graph Drawing for Very Large Graphs by Neural Networks

Authors: Ilan Hartskeerl, Tamara Mchedlidze, Simon van Wageningen, Peter Vangorp, and Alexandru Telea

Published in: LIPIcs, Volume 357, 33rd International Symposium on Graph Drawing and Network Visualization (GD 2025)

Abstract

tsNET is a recent graph drawing (GD) method that creates high quality layouts but suffers from a very high runtime. We present a new GD method, NNP-NET, which reduces tsNET’s time complexity to generate layouts for very large graphs in seconds. Additionally, we extend tsNET to support drawing graphs with edge weights. We accomplish this by replacing tsNET’s t-SNE projection with Neural Network Projection (NNP), a fast dimensionality reduction (DR) method that can imitate any given DR method. Our experiments show that NNP-NET gets good quality results when compared to other state-of-the art GD methods while yielding a better computational scalability.

Cite as

Ilan Hartskeerl, Tamara Mchedlidze, Simon van Wageningen, Peter Vangorp, and Alexandru Telea. NNP-NET: Accelerating t-SNE Graph Drawing for Very Large Graphs by Neural Networks. In 33rd International Symposium on Graph Drawing and Network Visualization (GD 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 357, pp. 22:1-22:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{hartskeerl_et_al:LIPIcs.GD.2025.22,
  author =	{Hartskeerl, Ilan and Mchedlidze, Tamara and van Wageningen, Simon and Vangorp, Peter and Telea, Alexandru},
  title =	{{NNP-NET: Accelerating t-SNE Graph Drawing for Very Large Graphs by Neural Networks}},
  booktitle =	{33rd International Symposium on Graph Drawing and Network Visualization (GD 2025)},
  pages =	{22:1--22:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-403-1},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{357},
  editor =	{Dujmovi\'{c}, Vida and Montecchiani, Fabrizio},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GD.2025.22},
  URN =		{urn:nbn:de:0030-drops-250087},
  doi =		{10.4230/LIPIcs.GD.2025.22},
  annote =	{Keywords: supervised graph drawing, dimensionality reduction, t-SNE}
}

Document

DOI: 10.4230/DagSemProc.09211.4

Comparison of Node-Link and Hierarchical Edge Bundling Layouts: A User Study

Authors: Alexandru Telea, Ozan Ersoy, Hessel Hoogendorp, and Dennie Reniers

Published in: Dagstuhl Seminar Proceedings, Volume 9211, Visualization and Monitoring of Network Traffic (2009)

Abstract

Visually investigating large network-like structures is a challenging task. Several approaches have been proposed in the past: node-link diagrams, adjacency matrices, and, more recently, hierarchical edge bundles. We present a recent experiment that compares the effectiveness of the classical node-link diagrams with the more recent hierarchical bundled edges. The users involved several computer science practitioners, the data ranged from graphs of several hundreds to several tens of hundreds of nodes, the tasks involved answering a number of structural overview as well as detailed questions involved system dependencies.

Cite as

Alexandru Telea, Ozan Ersoy, Hessel Hoogendorp, and Dennie Reniers. Comparison of Node-Link and Hierarchical Edge Bundling Layouts: A User Study. In Visualization and Monitoring of Network Traffic. Dagstuhl Seminar Proceedings, Volume 9211, pp. 1-12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2009)

Copy BibTex To Clipboard

@InProceedings{telea_et_al:DagSemProc.09211.4,
  author =	{Telea, Alexandru and Ersoy, Ozan and Hoogendorp, Hessel and Reniers, Dennie},
  title =	{{Comparison of Node-Link and Hierarchical Edge Bundling Layouts: A User Study}},
  booktitle =	{Visualization and Monitoring of Network Traffic},
  pages =	{1--12},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2009},
  volume =	{9211},
  editor =	{Daniel A. Keim and Aiko Pras and J\"{u}rgen Sch\"{o}nw\"{a}lder and Pak Chung Wong},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.09211.4},
  URN =		{urn:nbn:de:0030-drops-21542},
  doi =		{10.4230/DagSemProc.09211.4},
  annote =	{Keywords: Graph visualization, user studies, software visualization, call graphs}
}

Search Results

Documents authored by Telea, Alexandru

NNP-NET

Abstract

Cite as

NNP-NET: Accelerating t-SNE Graph Drawing for Very Large Graphs by Neural Networks

Abstract

Cite as

Comparison of Node-Link and Hierarchical Edge Bundling Layouts: A User Study

Abstract

Cite as

Thanks for your feedback!

Could not send message