Visualizing edge-edge relations in graphs

Abstract

Figure 1: Financial transaction data of 249 transactions between 181 accounts visualized as directed straight links connecting vertices and hence representing relations between objects. The blue curves represent edge-edge relations, thereby connecting pairs of transactions that vary in amount drastically, although assigned the same set of keywords. Left: Loops attached to transactions represent temporal patterns (emphasized by the green arrows), i.e., reoccurring transactions of diverging amounts between the same accounts. Right: Selection of four transactions whose amounts vary from many other transactions that have the same keywords. ABSTRACTGraphs are used to model relations between sets of objects. Objects are represented by vertices and relations by edges of the graph. Besides vertex-vertex relations, in some application domains also relations between edges exist. Our new visualization approach supports the investigation of both relation types in one diagram. Edge-edge relations are visualized as curves that are directly integrated into the node-link diagram that represents the object-relation structure. In contrast, vertex-vertex relations are illustrated distinguishably from edge-edge relations using straight links as representations. While the shape of links is used to differentiate between the relation types, the weights of the edge-edge relations are mapped to the width and color of the curves. To facilitate an extensive analysis of interrelations, our approach incorporates several interaction techniques that can be used for filtering and highlighting. The usability of our visualization is demonstrated with two case studies in the application domains of bioinformatics and financial services.

Visualizing Group Structures in Graphs: A Survey

“…We are aware of only one superimposed visualization technique, in particular, a line overlay approach. Vehlow et al [VHTW13] visualize pairs of edges-i.e. |E k | = 2-within a node-link diagram by connecting the respective links with curves ( Figure 8d).…”

“…Vehlow et al . [VHTW13] visualize pairs of edges—i.e. —within a node‐link diagram by connecting the respective links with curves (Figure d).…”

Dual Adjacency Matrix: Exploring Link Groups in Dense Networks

“…Bundling links by the position of their nodes in a predefined hierarchy reveals correlations between links and the properties of their nodes [Hol06]. Visual manipulation of network topology can be avoided via explicit visualization of link to link relations by introducing an extra type of link [VHTW13].…”