Recursive Principal Component Analysis of Graphs

Treatment of general structured information by neural networks is an emerging research topic. Here we show how representations for graphs preserving all the information can be devised by Recursive Principal Components Analysis learning. These representations are derived from eigenanalysis of extended vectorial representations of the input graphs. Experimental results performed on a set of chemical compounds represented as undirected graphs show the feasibility and effectiveness of the proposed approach.

• Type: Conference
• Year: 2007
• Where: ICANN
• Authors: Alessio Micheli, Alessandro Sperduti
• Keywords: ICANN 2007, Recursive Principal Components, Undirected Graphs, Vectorial Representations