BoG: A New Approach for Graph Matching
Fernanda B. Silva, Salvatore Tabbone, Ricardo da Silva Torres · 2014
Huge volume of graph data are becoming available. This scenario demands the development of effective and efficient methods to perform graph matching. In this paper, we propose to adapt the Bag-of-Words model into the context of graphs. Using a vocabulary based on graph local structures, we represent graphs as histograms. Experiments show that our approach achieves good accuracy rates. Moreover, the advantage of this representation is that the computation of graph matching has a very low complexity, which allows to efficiently perform graph classification and retrieval on large datasets.