Algorithms and Experiments Comparing Two Hierarchical Drawing Frameworks

TL;DR

This paper introduces improved algorithms for hierarchical graph drawing that optimize height, area, and bends, and compares them experimentally to existing frameworks, highlighting their advantages and trade-offs.

Contribution

The paper extends the path-based hierarchical drawing framework with algorithms that improve bounds and efficiency, and compares them to the Sugiyama framework.

Findings

Better area and bend counts in drawings

Worse crossings in sparse graphs

Efficient algorithms for path ordering

Abstract

We present algorithms that extend the path-based hierarchical drawing framework and give experimental results. Our algorithms run in $O(km)$ time, where $k$ is the number of paths and $m$ is the number of edges of the graph, and provide better upper bounds than the original path based framework: e.g., the height of the resulting drawings is equal to the length of the longest path of $G$, instead of $n-1$, where $n$ is the number of nodes. Additionally, we extend this framework, by bundling and drawing all the edges of the DAG in $O(m + n \log n)$ time, using minimum extra width per path. We also provide some comparison to a well known hierarchical drawing framework, widely known as the Sugiyama framework, as a proof of concept. The experimental results show that our algorithms produce drawings that are better in area and number of bends, but worse for crossings in sparse graphs. Hence, our technique offers an interesting alternative for drawing hierarchical graphs. Finally, we present an $O(m + k \log k)$ time algorithm that computes a specific order of the paths in order to reduce the total edge length and number of crossings and bends.