Can an NN model plainly learn planar layouts?
This addresses the problem of automated graph visualization for researchers and practitioners, but appears incremental as it builds on existing neural network methods.
The researchers investigated whether neural networks can learn to generate planar graph layouts, finding they outperform conventional techniques for certain graph classes but are more susceptible to data randomness and less robust than expected.
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.