复杂网络搜索中优化全局平均首达时间的随机游走器选择
Selection of Random Walkers that Optimizes the Global Mean First-Passage Time for Search in Complex Networks
摘要:
设计了一种方法来优化多个随机游走者在复杂网络中搜索一般目标的全局平均首达时间(GMFPT),而不需要指定目标节点的属性.根据GMFPT的拉普拉斯变换公式,我们可以等价地最小化随机行走者访问的站点的概率分布之间的重叠。我们采用了一种只变异的遗传算法来解决这个优化问题,使用不同的起始位置和相应的变异矩阵来修改它们的人口的步行者。在两种随机网络(WS和BA)上的数值实验表明,在选择步行者的起点以实现最小重叠方面取得了令人满意的结果。因此,我们的方法提供了指导,建立搜索过程中的复杂网络上的多个随机游走。
英文摘要:
We design a method to optimize the global mean first-passage time (GMFPT) of multiple random walkers searching in complex networks for a general target, without specifying the property of the target node. According to the Laplace transformed formula of the GMFPT, we can equivalently minimize the overlap between the probability distribution of sites visited by the random walkers. We employ a mutation only genetic algorithm to solve this optimization problem using a population of walkers with different starting positions and a corresponding mutation matrix to modify them. The numerical experiments on two kinds of random networks (WS and BA) show satisfactory results in selecting the origins for the walkers to achieve minimum overlap. Our method thus provides guidance for setting up the search process by multiple random walkers on complex networks.
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。