Minimum weighted mining in frequent directed subgraphs

Weighted directed graph, being the abstract model of traffic network structure, is the hotspot of data mining research currently. This paper aims at mining weighted directed graph, two kinds of new algorithms are proposed and a connected complete subgraph could be obtained. The first algorithm WDSpan compares the value of weight on the basis of using depth-first search strategy to complete integral mining; The second algorithm called MWD takes the product of different subgraph sizes´ average weights and support as a new calculation measure, the factor of weight is considered in the process of mining, and finds the minimum weight subgraphs of different models in subgraphs that meet the condition. Experimental results show that the algorithm reduces the space of memory.