2026-07-25T09:51:06Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:25008 2026-02-09T07:53:29Z ddc:004 open_access

NNP-NET: Accelerating t-SNE Graph Drawing for Very Large Graphs by Neural Networks Hartskeerl, Ilan Mchedlidze, Tamara van Wageningen, Simon Vangorp, Peter Telea, Alexandru supervised graph drawing dimensionality reduction t-SNE 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. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Ilan Hartskeerl and Tamara Mchedlidze and Simon van Wageningen and Peter Vangorp and Alexandru Telea 2025 Is Part Of LIPIcs, Volume 357, 33rd International Symposium on Graph Drawing and Network Visualization (GD 2025) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.GD.2025.22 urn:nbn:de:0030-drops-250087 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.GD.2025.22 eng https://creativecommons.org/licenses/by/4.0/legalcode