arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.11279cs.LGcs.AIstat.ML
收藏

基于强化学习的目标有向图构造

Goal-directed graph construction using reinforcement learning

University College London(伦敦大学学院);The Alan Turing Institute(阿兰·图灵研究所);University of Bologna(博洛尼亚大学)

Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

摘要:

图形可以用来表示和推理系统,并且已经设计了各种度量来量化它们的全局特性。然而,目前很少有人知道如何构建一个图或改善现有的给定目标。在这项工作中,我们制定了一个图形的建设作为一个决策过程中,中央代理创建拓扑结构的试错和接收奖励成比例的目标的价值。通过这个概念框架,我们提出了一种基于强化学习和图神经网络的算法来学习图的构造和改进策略。我们的核心案例研究侧重于对故障和攻击的鲁棒性,这是一个与为现代社会提供动力的基础设施和通信网络相关的属性。在合成图和真实世界图上的实验表明,这种方法可以优于现有方法,同时评估成本更低。它还允许泛化到样本外图,以及在某些情况下更大的分布外图。该方法也适用于图的其他全局结构性质的优化。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑