提出了一种基于关联矩阵的频繁子图挖掘算法。
An algorithm for mining frequent subgraphs based on associated matrix was proposed.
频繁子图挖掘主要涉及到子图搜索和子图同构问题。
Frequent subgraph mining includes subgraph search and isomorphism problems.
随着图的广泛应用，图的规模不断扩大，因此提高频繁子图挖掘效率势在必行。
Therefore it is imperative to improve the efficiency of mining the frequent subgraphs.
其次，将频繁子图边扩展及同构判断这部分频繁子图挖掘算法中时间复杂度最高的部分并行处理。
Secondly, we processed the edge expansion and frequent sub-graph isomorphism which are the most complexity parts of frequent subgraphs mining in parallel.
随着对大量结构化数据分析需求的增长，从图集合中挖掘频繁子图模式已经成为数据挖掘领域的研究热点。
With the increasing demand of massive structured data analysis, mining frequent subgraph patterns from graph datasets has been an attention-deserving field.
一种解决的方法就是用图的形式表示这些领域的事务，然后利用基于图论的数据挖掘技术发现频繁子图。
An alternate way to solve these problems is to represent the transactions of those domains by graph, and find the frequent subgraphs by using graph-based data mining techniques.
为解决上述问题，提出了一种深度优先的挖掘加权最大频繁子图的新算法。
To solve the above two problems, authors propose a new depth-first algorithm to discover weighted maximal frequent subgraphs only.
为解决上述问题，提出了一种深度优先的挖掘加权最大频繁子图的新算法。
To solve the above two problems, authors propose a new depth-first algorithm to discover weighted maximal frequent subgraphs only.
应用推荐