Abstract:Abstract.We report an experience on a practical system for drawing hypergraphs in the subset standard. The Patate system is based on the application of a classical force directed method to a dynamic graph, which is deduced, at a given iteration time, from the hypergraph structure and particular vertex locations. Different strategies to define the dynamic underlying graph are presented. We illustrate in particular the method when the graph is obtained by computing an Euclidean Steiner tree.
“…Bertault and Eades [5] propose several methods to build the graph corresponding to a given hypergraph that give reasonable results for small hypergraphs, but becomes too cluttered when the number of nodes, the size of hyperedges and the degree of overlapping grow. 20 nodes, with about 10 hyperedges of length (at most) 5 are enough to clutter the visualization.…”
Section: Drawing Of Euler Diagrams and Hypergraphsmentioning
confidence: 99%
“…When the complexity of data grows, it is useful to abstract from basic groups to intersection groups that may show, for example, consensus on gene groups, coincidence [4] low (3)(4)(5)(6)(7)(8) yes no contours Subset standard [5] low (∼ 10) yes points contours BiVoc [6] medium (∼ 20) yes (duplications) rows and columns rectangles Johnson and Krempel [7] low yes (projection) piecharts projected to a grid lines KartOO [8] low yes (projection) icons surfaces HCG [9] medium (∼ 20) inclusion no polygons Compound Graphs [10] medium (∼ 50) inclusion labels rectangles SocialAction [11] medium (∼ 20) no labels colored areas Vizster [12] medium (∼ 20) no icons colored areas Omote and Sugiyama [13] on database searches or relevance on social groups. Transparency and the design of special icons will be used in order to achieve this.…”
SUMMARYHypergraphs drawn in the subset standard are useful to represent group relationships using topographic characteristics such as intersection, exclusion and enclosing. However, they present cluttering when dealing with a moderately high number of nodes (more than 20) and large hyperedges (connecting more than 10 nodes, with three or more overlapping nodes). At this complexity level, a study of the visual encoding of hypergraphs is required in order to reduce cluttering and increase the understanding of larger sets. Here we present a graph model and a visual design that help in the visualization of group relationships represented by hypergraphs. This is done by the use of superimposed visualization layers with different abstraction levels and the help of interaction and navigation through the display.
“…Bertault and Eades [5] propose several methods to build the graph corresponding to a given hypergraph that give reasonable results for small hypergraphs, but becomes too cluttered when the number of nodes, the size of hyperedges and the degree of overlapping grow. 20 nodes, with about 10 hyperedges of length (at most) 5 are enough to clutter the visualization.…”
Section: Drawing Of Euler Diagrams and Hypergraphsmentioning
confidence: 99%
“…When the complexity of data grows, it is useful to abstract from basic groups to intersection groups that may show, for example, consensus on gene groups, coincidence [4] low (3)(4)(5)(6)(7)(8) yes no contours Subset standard [5] low (∼ 10) yes points contours BiVoc [6] medium (∼ 20) yes (duplications) rows and columns rectangles Johnson and Krempel [7] low yes (projection) piecharts projected to a grid lines KartOO [8] low yes (projection) icons surfaces HCG [9] medium (∼ 20) inclusion no polygons Compound Graphs [10] medium (∼ 50) inclusion labels rectangles SocialAction [11] medium (∼ 20) no labels colored areas Vizster [12] medium (∼ 20) no icons colored areas Omote and Sugiyama [13] on database searches or relevance on social groups. Transparency and the design of special icons will be used in order to achieve this.…”
SUMMARYHypergraphs drawn in the subset standard are useful to represent group relationships using topographic characteristics such as intersection, exclusion and enclosing. However, they present cluttering when dealing with a moderately high number of nodes (more than 20) and large hyperedges (connecting more than 10 nodes, with three or more overlapping nodes). At this complexity level, a study of the visual encoding of hypergraphs is required in order to reduce cluttering and increase the understanding of larger sets. Here we present a graph model and a visual design that help in the visualization of group relationships represented by hypergraphs. This is done by the use of superimposed visualization layers with different abstraction levels and the help of interaction and navigation through the display.
“…Hence, modulo re-labeling of vertices and the removal of white non-vertex faces, we must have a subdivision drawing as the one depicted in Fig. 5(a) with a non-simple hyperedge region for hyperedge (2,3,4). Second, consider the hypergraph H 2 that is schematically depicted in Fig.…”
Section: Observation 1 a Hypergraph H (I) Has A Simple Subdivision Dmentioning
confidence: 99%
“…Subset-based drawings neither know any concept of or experience any problems with planarity. Bertault and Eades [2] show how to create subset-based hypergraph drawings.…”
Section: Introductionmentioning
confidence: 99%
“…2(a, b)). Concerning vertex-planarity, consider the following hypergraph H: H has six vertices and three hyperedges (1, 2, 3, 4), (1,2,3,5), and (1, 2, 3, 6). H is vertex-planar but not (Zykov-)planar.…”
Abstract. We introduce the concept of subdivision drawings of hypergraphs. In a subdivision drawing each vertex corresponds uniquely to a face of a planar subdivision and, for each hyperedge, the union of the faces corresponding to the vertices incident to that hyperedge is connected. Vertex-based Venn diagrams and concrete Euler diagrams are both subdivision drawings. In this paper we study two new types of subdivision drawings which are more general than concrete Euler diagrams and more restricted than vertex-based Venn diagrams. They allow us to draw more hypergraphs than the former while having better aesthetic properties than the latter.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.