Interpreting Graph Drawing with Multi-Agent Reinforcement Learning.

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