探讨演变图(即随时间变化的图)的挖掘,重点研究在演变图中挖掘连接子图的演变模式集合.提出一种连接子图的相似度函数及其快速计算算法.基于该相似度函数,提出一种发现演变模式集合的多项式时间复杂度的动态规划算法.模拟数据集上的实验结果表明,该算法具有较低的误差率和较高的效率.真实数据集上的实验结果表明,挖掘结果在真实应用中具有实际意义.
This paper investigates into the problem of mining evolving graphs, i.e. graphs changing over time. It focuses on mining evolving pattern set of connection subgraphs between given vertices in an evolving graph. A similarity function of connection subgraphs and the algorithm to compute it have been presented. Based on this similarity function, a dynamic programming algorithm with polynomial time complexity is proposed to find evolving pattern set. The experimental results on synthetic datasets show that the proposed algorithm has low error rate and high efficiency. The mining results on real datasets illustrate that the mining results have practical significance in real applications.