Selection Strategies for Ambiguous Graph Matching by Evolutionary Optimisation

摘要

This paper considers how ambiguous graph matching can be realised using a hybrid genetic algorithm. The problem we address is how to maximise the solution yield of the genetic algorithm when the available attributes are ambiguous. We focus on the role of the selection operator. A multi-modal evolutionary optimisation framework is proposed, which is capable of simultaneously producing several good alternative solutions. Unlike other multi-modal genetic algorithms, the one reported here requires no extra parameters: solution yields are maximised by removing bias in the selection step, while optimisation performance is maintained by a local search step.