FlexGD: A flexible force-directed model for graph drawing

Abstract

We propose FlexGD, a force-directed algorithm for straightline undirected graph drawing. The algorithm strives to draw graph layouts encompassing from uniform vertex distribution to extreme structure abstraction. It is flexible for it is parameterized so that the emphasis can be put on either of the two drawing criteria. The parameter determines how much the edges are shorter than the average distance between vertices. Extending the clustering property of the LinLog model, FlexGD is efficient for cluster visualization in an adjustable level. The energy function of FlexGD is minimized through a multilevel approach, particularly designed to work in contexts where edge length distribution is not uniform. Applying FlexGD on several real datasets, we illustrate both the good quality of the layout on various topologies, and the ability of the algorithm to meet the addressed drawing criteria.