Interpreting Graph Drawing with Multi-Agent Reinforcement Learning

TL;DR

This paper presents a novel approach to graph drawing by framing it as a multi-agent reinforcement learning problem, unifying classic algorithms and enabling new methods through reward function design.

Contribution

It introduces a MARL framework for graph drawing that unifies existing algorithms and facilitates the creation of new algorithms via diverse reward functions.

Findings

MARL can replicate classic graph drawing algorithms.

The MARL-based layouts are aesthetically comparable to traditional methods.

The framework supports developing new graph drawing algorithms.

Abstract

Applying machine learning techniques to graph drawing has become an emergent area of research in visualization. In this paper, we interpret graph drawing as a multi-agent reinforcement learning (MARL) problem. We first demonstrate that a large number of classic graph drawing algorithms, including force-directed layouts and stress majorization, can be interpreted within the framework of MARL. Using this interpretation, a node in the graph is assigned to an agent with a reward function. Via multi-agent reward maximization, we obtain an aesthetically pleasing graph layout that is comparable to the outputs of classic algorithms. The main strength of a MARL framework for graph drawing is that it not only unifies a number of classic drawing algorithms in a general formulation but also supports the creation of novel graph drawing algorithms by introducing a diverse set of reward functions.