Pattern Recognition, International Conference on (2002)
Quebec City, QC, Canada
Aug. 11, 2002 to Aug. 15, 2002
Bin Luo , University of York and Anhui University
Richard C. Wilson , University of York
Edwin R. Hancock , University of York
In this paper, we demonstrate how PCA and ICA can be used for embedding graphs in pattern-spaces. Graph spectral feature vectors are calculated from the leading eigen-values and eigenvectors of the unweighted graph adjacency matrix. The vectors are then embedded in a lower dimensional pattern space using both the PCA and ICA decomposition methods. Synthetic and real sequences are tested using the proposed graph clustering algorithm. The preliminary results show that generally speaking the ICA is better than PCA for clustering graphs. The best choice of graph spectral feature for clustering is the cluster shared perimeters.
B. Luo, R. C. Wilson and E. R. Hancock, "The Independent and Principal Component of Graph Spectra," Pattern Recognition, International Conference on(ICPR), Quebec City, QC, Canada, 2002, pp. 20164.