A Hybrid EA Approach with Cooperation between Individuals to Substructure Discovery in Graphical Databases

Abstract

A hybrid EA based algorithm is developed to discover potentially usefull substructures from graphical databases. During the searching process, losing instances is very common and vital to the algorithm performance. To address this issue, an individual cooperation operator is proposed, which enables different individuals to search the same substructure in a cooperative way. In addition, a new mechanism is also proposed to preserve the diversity regarding both the composition of an individual and the composition of the whole population. Experimental results show that these hybrid scheme successfully enhances the searching capability of the algorithm and improves the qualities of solutions.