cgSpan: Pattern Mining in Conceptual Graphs
This work addresses pattern mining for knowledge representation in Conceptual Graphs, but it is incremental as it builds on an existing algorithm with domain-specific extensions.
The authors tackled the problem of frequent pattern mining in Conceptual Graphs (CGs) by proposing cgSpan, an algorithm that extends DMGM-GSM to incorporate CG-specific knowledge like fixed arity, signatures, and inference rules, resulting in a faster algorithm with more expressive results and less redundancy.
Conceptual Graphs (CGs) are a graph-based knowledge representation formalism. In this paper we propose cgSpan a CG frequent pattern mining algorithm. It extends the DMGM-GSM algorithm that takes taxonomy-based labeled graphs as input; it includes three more kinds of knowledge of the CG formalism: (a) the fixed arity of relation nodes, handling graphs of neighborhoods centered on relations rather than graphs of nodes, (b) the signatures, avoiding patterns with concept types more general than the maximal types specified in signatures and (c) the inference rules, applying them during the pattern mining process. The experimental study highlights that cgSpan is a functional CG Frequent Pattern Mining algorithm and that including CGs specificities results in a faster algorithm with more expressive results and less redundancy with vocabulary.