Scalable mining of large disk-based graph databases

Abstract

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

Patterns on the Connected Components of Terabyte-Scale Graphs

“…Graph Mining: There exists lots of "graph mining" algorithms: subgraph discovery(e.g., [12], [13], gPrune [14], gApprox [15], gSpan [16], Subdue [17], ADI [18], CSV [19]), computing communities (eg., [20], DENGRAPH [21], METIS [22]), attack detection [23], with too many alternatives for each of the above tasks. They are not directly related to the focus of this paper which is the static and dynamic structures of real networks.…”

Techniques for mining the design of e-government services to enhance end-user experience

“…However, graph mining appears in many contexts including bioinformatics and chemistry, and therefore, quite a few heuristics have been proposed to face this problem. The most prominent approaches include gSpan (Yan and Han, 2002), CloseGraph (Yan and Han, 2003) and ADI (Wang et al, 2004). In the following, we provide some notation prior to reducing the problem to graph mining.…”

Discovering Re-usable Design Solutions in Web Conceptual Schemas: Metrics and Methodology

“…However, graph mining appears in many contexts including bioinformatics and chemistry and therefore quite a few heuristics have been proposed to face this problem. The most prominent approaches include gSpan [25], CloseGraph [24] and ADI [21]. In the following we provide some notation prior to reducing the problem to graph mining.…”

“…Once having transformed all site views with the same methodology, design construct identification is reduced to mining frequent subgraphs of the site view database. The latter can be accomplished with any of the methodologies in [21], [24], [25] provided the desired support 2 is given.…”