As a data mining process, graph mining is used to find and to extract patterns from graph data structure. A graph is a network of nodes that also describes the realtionship and the interaction between them. Graphs are used for the description of complicated structures such as biological structures, social networks, images, circuits, workflows or XML documents.
With an increasing amount of graphs, also the need of processes for extracting patterns of interest from large structured data sets is gaining importance. The description of the underlying data can be used for classification or clustering. Whereas traditional data mining uncovers sub-patterns and interferences of text elements, graph mining extracts the sub-structure of graphs and the links between elements of structured data. Even if graph mining algorithms can extract various information from graphs, frequent structurers are the very basic patterns which are discovered in graph mining processes. These frequent strucuters facilitate similarity search in graph data bases and are useful for characterising, classifying and clustering.
Borgwardt, K., Böttger, S., & Kriegel, H.-P. (2006). Graph mining. SIGMOD 06 Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data
Borgwardt, K. M., & Yan, X. (2008). Graph Mining and Graph Kernels. Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 08