Our paper has been accepted at PAKDD2011, an international conference for data-mining. The paper is about a novel mining algorithm from linear graphs. This is joint work with Daisuke Okanohara from Preferred Infrastructure, Shuichi Hirose and Koji Tsuda from AIST. I've uploaded the paper in arxiv.org.
LGM: Mining Frequent Subgraphs from Linear Graphs, Yasuo Tabei, Daisuke Okanohara, Shuichi Hirose, Koji Tsuda, The 15th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD2011), link to the paper
Linear graph is a graph whose vertices are totally ordered. Biological and linguistic sequences with interactions among symbols are naturally represented as linear graphs. Examples include protein contact maps, RNA secondary structures and predicate-argument structures. In this paper, we designed an algorithm for mining all frequent subgraphs from linear graphs by applying the reverse search technique.
I've uploaded a power point slide in the following.