subgraph matching using graph neural network使用神经网络图子图匹配.pdf

Journal of Intelligent Learning Systems and Applications, 2012, 4, 274-278 / 10.4236/jilsa.2012.44028 Published Online November 2012 (http://www.SciRP.org/journal/jilsa) Subgraph Matching Using Graph Neural Network GnanaJothi Raja Baskararaja, MeenaRani Sundaramoorthy Manickavasagam Department of Mathematics, V. V. Vanniaperumal College for Women, Virudhunagar, India. Email: gnanajothi_pcs@, smmeenarani@ Received May 4th st th , 2012; revised August 1 , 2012; accepted August 8 , 2012 ABSTRACT Subgraph matching problem is identifying a target subgraph in a graph. Graph neural network (GNN) is an artificial neural network model which is capable of processing general types of graph structured data. A graph may contain many subgraphs isomorphic to a given target graph. In this paper GNN is modeled to identify a subgraph that matches the target graph along with its characteristics. The simulation results show that GNN is capable of identifying a target sub- graph in a graph. Keywords: Subgraph Matching; Graph Neural Network; Backpropagation; Recurrent Neural Network; Feedforward Neural Network 1. Introduction [1], Clique problem [2], Half Hot problem [2], and Tree depth problem [2]. A. Pucci, M. Gori, M. Hagenbuchner, In many practical and engineering applications the un- F. Scarselli, and A. C. Tsoi [3] have applied GNN to the derlying data are often represented in terms of graphs. movie lens data set and have discussed the problems and Graphs generally represent a set of objects (nodes) and