Goal-directed graph construction using reinforcement learning
This addresses the challenge of optimizing global structural properties of graphs, like robustness in infrastructure networks, with a novel method that is incremental in applying RL to graph construction.
The paper tackles the problem of constructing or improving graphs to meet a target objective, such as robustness to failures, by formulating it as a reinforcement learning process and proposing an algorithm based on reinforcement learning and graph neural networks. Experiments show it outperforms existing methods, is cheaper to evaluate, and generalizes to out-of-sample and larger graphs.
Graphs can be used to represent and reason about systems and a variety of metrics have been devised to quantify their global characteristics. However, little is currently known about how to construct a graph or improve an existing one given a target objective. In this work, we formulate the construction of a graph as a decision-making process in which a central agent creates topologies by trial and error and receives rewards proportional to the value of the target objective. By means of this conceptual framework, we propose an algorithm based on reinforcement learning and graph neural networks to learn graph construction and improvement strategies. Our core case study focuses on robustness to failures and attacks, a property relevant for the infrastructure and communication networks that power modern society. Experiments on synthetic and real-world graphs show that this approach can outperform existing methods while being cheaper to evaluate. It also allows generalization to out-of-sample graphs, as well as to larger out-of-distribution graphs in some cases. The approach is applicable to the optimization of other global structural properties of graphs.