PT Unknown
AU Jaume Gibert
   Ernest Valveny
TI Graph Embedding based on Nodes Attributes Representatives and a Graph of Words Representation.
BT 13th International worshop on structural and syntactic pattern recognition and 8th international worshop on statistical pattern recognition
PY 2010
BP 223–232
VL 6218
DI 10.1007/978-3-642-14980-1_21
AB Although graph embedding has recently been used to extend statistical pattern recognition techniques to the graph domain, some existing embeddings are usually computationally expensive as they rely on classical graph-based operations. In this paper we present a new way to embed graphs into vector spaces by first encapsulating the information stored in the original graph under another graph representation by clustering the attributes of the graphs to be processed. This new representation makes the association of graphs to vectors an easy step by just arranging both node attributes and the adjacency matrix in the form of vectors. To test our method, we use two different databases of graphs whose nodes attributes are of different nature. A comparison with a reference method permits to show that this new embedding is better in terms of classification rates, while being much more faster.
ER