摘要
提出了一种基于关联矩阵的频繁子图挖掘算法。该算法通过对关联矩阵的标准化,有效地降低了子图同构判断的代价。在此基础上,算法利用深度优先的思想,通过逐步扩展频繁边找出所有频繁子图。实验结果表明,该算法比其他同类算法具有更快的速度和更好的稳定性。
An algorithm for mining frequent subgraphs based on associated matrix was proposed. By normalizing the associated matrix of the graph, the computational cost on verifying the isomorphism of the subgraphs was effectively reduced. Based on the depth-first searching method, all the frequent subgraphs could be searched by adding edges progressively. Experimental results show that the algorithm has higher speed and better stability than other similar ones.
出处
《计算机应用》
CSCD
北大核心
2008年第10期2533-2536,2557,共5页
journal of Computer Applications
基金
国家科技攻关项目(2003BA614A-14)
国家自然科学基金资助项目(60673060)
江苏省自然科学基金资助项目(BK2005047)
南京大学软件新技术国家重点实验室开放基金资助项目
关键词
图
关联矩阵
同构
数据挖掘
graph
associated matrix
isomorphism
data mining
