Scalable mining of large disk-based graph databases

摘要: Mining frequent structural patterns from graph databases is an interesting problem with broad applications. Most of the previous studies focus on pruning unfruitful search subspaces effectively, but few them address mining large, disk-based databases. As many in applications cannot be held into main memory, scalable remains a challenging problem. In this paper, we develop effective index structure, ADI (for adjacency index), to support various over large that memory. The simple and efficient build. Moreover, new structure can easily adopted existing pattern algorithms. example, adapt well-known gSpan algorithm by using structure. experimental results show enables one set experiments, method mine million graphs, while original only handle up 300 thousand graphs. our faster than when both run