MULTI-NETVIS: Visual Analytics for Multivariate Network

Abstract

In the process of multivariate network exploration and analysis, it is important to consider network topology and attribute correlation analysis. In order to consider both in presentation and analysis, existing research focuses on visual design and multiple-view visualization. However, this multitudinous visual design makes network cognition and analysis difficult. In multi-view visualization, the associated information among attributes is rarely retained and is often accompanied by tedious interaction processes. In this paper, a layout scheme is proposed to balance attribute and topology analysis in multivariate network visual analysis and a multivariate network visual analytics system is implemented based on the layout scheme. The analysis scenarios of overall, community, and local multi-granularity are provided by the layout scheme, which combines 3D, 2.5D, and 2D layouts. According to the layout scheme, we propose a layout transformation method to maintain the relative position of the topological context layouts in three dimensions. Furthermore, we propose a Louvain-3D FDA layout algorithm for the 3D layout, and introduce an edge bundling algorithm in the 2.5D layout to achieve an attribute-oriented topology layout. Combining the principle of interaction from global to detail, we design a novel system, Multi-NetVis, which supports users in drilling exploration and analysis and takes both the network attribute correlations and topological structure into consideration. Finally, two datasets are selected to demonstrate the usage scenarios and an evaluation experiment is designed to verify the effectiveness of the layout scheme.