A Many-objective Evolutionary Algorithm Approach for Graph Visualization

Determining the layout of a graph from an aesthetic point-of-view is a challenging task and becomes difficult with the increase in complexity of a graph. Aesthetic attributes of graphs can be captured in terms of metrics such as the number of edge crossings, uniform edge lengths, visualization of loops in causal loop diagrams, and a minimum distance between neighboring nodes. These metrics are then used as objectives in an evolutionary algorithm to obtain the optimal set of trade-off solutions, leading to a pleasing layout. As the number of aesthetic measures could be more than three, we propose a framework based on a many-objective evolutionary algorithm to produce aesthetically pleasing graph layouts. The outcome of this approach is compared with the ForceAtlas2 force-directed layout algorithm and the proposed approach demonstrates better results for the objectives.