HUSM: High utility subgraph mining in single graph databases

Information Sciences(2024)

引用 0|浏览3
暂无评分
摘要
Frequent subgraph mining (FSM) is a crucial research area with diverse applications. However, traditional FSM treats all subgraphs as equally important. In practical applications, some subgraphs may be frequent but not very valuable, while others may be infrequent but highly valuable. To address this issue, we introduce utility pattern mining into graph mining, enabling the discovery of meaningful patterns based on user interest rather than relying solely on support. We define utility functions in single graph databases and formally define the problem of high utility subgraph mining (HUSM). In the face of several challenges posed by this new problem, such as the absence of downward closure property and a large number of candidates, we design several utility upper bounds that satisfy the downward closure property. We then develop a HUSM algorithm to efficiently mine all high utility subgraphs in single graph databases. Additionally, we design a lossless concise representation for high utility subgraphs, which has fewer instances than the total number of high utility subgraphs and can derive all of them, making the mining results more representative. The experimental results demonstrate that our method exhibits excellent performance, and the concise representation plays a significant role in simplifying the mining results.
更多
查看译文
关键词
Utility pattern mining,Concise representation,Graph mining,Pattern mining
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要