Can an NN model plainly learn planar layouts?

Research output: Contribution to conferencePosterAcademic

Abstract

Planar graph drawings tend to be aesthetically pleasing. In this poster we explore a Neural Network's capability of learning various planar graph classes. Additionally, we also investigate the effectiveness of the model in generalizing beyond planarity. We find that the model can outperform conventional techniques for certain graph classes. The model, however, appears to be more susceptible to randomness in the data, and seems to be less robust than expected.
Original languageEnglish
Pages476
Number of pages479
Publication statusPublished - 2022
Event30th International Symposium, Graph Drawing and Network Visualization - Japan, Tokyo, Japan
Duration: 13 Sept 202216 Sept 2022
Conference number: 30

Conference

Conference30th International Symposium, Graph Drawing and Network Visualization
Abbreviated titleGD
Country/TerritoryJapan
CityTokyo
Period13/09/2216/09/22

Keywords

  • Neural Networks
  • Machine Learning
  • Graph Drawing
  • Planarity

Fingerprint

Dive into the research topics of 'Can an NN model plainly learn planar layouts?'. Together they form a unique fingerprint.

Cite this