Matching of attributed and nonattributed graphs by use of a Boltzmann machine algorithm
Peter Kuner · International Conference on Artificial Neural Networks · 1989
The paper deals with the task of solving the pure topological subgraph isomorphism problem and with the finding of a best relational matching subgraph to a given reference graph in an image graph with respect to both graphs' attributes. In both cases, a combination of a simulated annealing strategy and of a Hungarian method algorithm is used. This combined strategy performs faster than the relaxation method and gives comparable results. It has two advantages. First, optimization over the states' probability space is easier than generating the states themselves. Second, this principle renders very complex optimization possible by use of a simple and fast integer programming tool. >