Network Layout Visualization Based on Sammon's Projection

Visualization is an important part of Network Analysis. It helps to find features of the network that are not easily identifiable. In this paper we present our approach to the visualization of weighted networks based on Sammon's projection. The network may be seen as a set of data points in the space induced by the incidence relation or as a symmetric matrix of vertex distances. We propose several methods for construction of the input for the Sammon's projection and discuss the effect of the particular methods on the final layout. Results are illustrated using several networks in the 2D layout. Presented experiments use the well-known Karate club network and weighted co-authors network based on the DBLP database.