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 language | English |
|---|---|
| Pages | 476 |
| Number of pages | 479 |
| Publication status | Published - 2022 |
| Event | 30th International Symposium, Graph Drawing and Network Visualization - Japan, Tokyo, Japan Duration: 13 Sept 2022 → 16 Sept 2022 Conference number: 30 |
Conference
| Conference | 30th International Symposium, Graph Drawing and Network Visualization |
|---|---|
| Abbreviated title | GD |
| Country/Territory | Japan |
| City | Tokyo |
| Period | 13/09/22 → 16/09/22 |
Keywords
- Neural Networks
- Machine Learning
- Graph Drawing
- Planarity