A Joint Spectral Similarity Measure for Graphs Classification

Abstract In spite of the simple linear relationship between the adjacency A and the Laplacian L matrices, L = D − A where D is the degrees matrix, these matrices seem to reveal informations about the graph in different ways, where it appears that some details are detected only by one of them, as in the case of cospectral graphs. Based on this observation, a new graphs similarity measure, referred to as joint spectral similarity ( JSS ) incorporating both spectral information from A and L is introduced. A weighting parameter to control the relative influence of each matrix is used. Furthermore, to highlight the overlapping and the unequal contributions of these matrices for graph representation, they are compared in terms of the so called Von Neumann entropy (VN), connectivity and complexity measures. The graph is viewed as a quantum system and thus, the calculated VN entropy of its perturbed density matrix emphasizes the overlapping in terms of information quantity of A and L matrices. The impact of matrix representation is strongly illustrated by classification findings on real and conceptual graphs based on JSS measure. The obtained results show the effectiveness of the JSS measure in terms of graph classification accuracies and also highlight varying information overlapping rates of A and L , and point out their different ways in recovering structural information of the graph.

[1]  Jérôme Kunegis,et al.  Exploiting The Structure of Bipartite Graphs for Algebraic and Spectral Graph Theory Applications , 2014, Internet Math..

[2]  Hans-Peter Kriegel,et al.  Protein function prediction via graph kernels , 2005, ISMB.

[3]  Kristian Kersting,et al.  Glocalized Weisfeiler-Lehman Graph Kernels: Global-Local Feature Maps of Graphs , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[4]  S. V. N. Vishwanathan,et al.  Graph kernels , 2007 .

[6]  B. McKay,et al.  Constructing cospectral graphs , 1982 .

[7]  Edwin R. Hancock,et al.  An Aligned Subtree Kernel for Weighted Graphs , 2015, ICML.

[8]  I. Gutman,et al.  Laplacian energy of a graph , 2006 .

[9]  Nils M. Kriege,et al.  On Valid Optimal Assignment Kernels and Applications to Graph Classification , 2016, NIPS.

[10]  José M. F. Moura,et al.  Discrete Signal Processing on Graphs: Frequency Analysis , 2013, IEEE Transactions on Signal Processing.

[11]  Xiao-yu Chen.  Perturbation theory of von Neumann Entropy , 2009, 0902.4733.

[12]  W. Haemers,et al.  Which graphs are determined by their spectrum , 2003 .

[13]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[14]  R. Merris.  Large families of laplacian isospectral graphs , 1997 .

[15]  Thomas Gärtner,et al.  On Graph Kernels: Hardness Results and Efficient Alternatives , 2003, COLT.

[16]  Edwin R. Hancock,et al.  Quantum kernels for unattributed graphs using discrete-time quantum walks , 2017, Pattern Recognit. Lett..

[17]  Simone Severini,et al.  Quantifying Complexity in Networks: The von Neumann Entropy , 2009, Int. J. Agent Technol. Syst..

[18]  Yongtang Shi,et al.  Note on the energy of regular graphs , 2009 .

[19]  M. Fiedler.  Algebraic connectivity of graphs , 1973 .

[20]  Lucas Lacasa,et al.  From time series to complex networks: The visibility graph , 2008, Proceedings of the National Academy of Sciences.

[21]  Kurt Mehlhorn,et al.  Weisfeiler-Lehman Graph Kernels , 2011, J. Mach. Learn. Res..

[22]  Zoran Stanić,et al.  Spectral distances of graphs based on their different matrix representations , 2014 .

[23]  P. Dobson,et al.  Distinguishing enzyme structures from non-enzymes without alignments. , 2003, Journal of molecular biology.

[24]  Antje Chang,et al.  BRENDA , the enzyme database : updates and major new developments , 2003 .

[25]  Edwin R. Hancock,et al.  Graph characterizations from von Neumann entropy , 2012, Pattern Recognit. Lett..

[26]  José Antonio de la Peña,et al.  ON THE ENERGY OF REGULAR GRAPHS , .

[27]  Hisashi Kashima,et al.  Marginalized Kernels Between Labeled Graphs , 2003, ICML.

[28]  Edwin R. Hancock,et al.  A quantum Jensen-Shannon graph kernel for unattributed graphs , 2015, Pattern Recognit..

[29]  G. Karypis,et al.  Acyclic Subgraph Based Descriptor Spaces for Chemical Compound Retrieval and Classification , 2006 .

[30]  D. A. Edwards.  The mathematical foundations of quantum mechanics , 1979, Synthese.

[31]  G. Bianconi,et al.  Shannon and von Neumann entropy of random networks with heterogeneous expected degree. , 2010, Physical review. E, Statistical, nonlinear, and soft matter physics.

[32]  A. Debnath,et al.  Structure-activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. , 1991, Journal of medicinal chemistry.

[33]  S. Severini,et al.  The Laplacian of a Graph as a Density Matrix: A Basic Combinatorial Approach to Separability of Mixed States , 2004, quant-ph/0406165.

[34]  Edwin R. Hancock,et al.  Jensen-Shannon graph kernel using information functionals , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[35]  Mario Vento,et al.  Thirty Years Of Graph Matching In Pattern Recognition , 2004, Int. J. Pattern Recognit. Artif. Intell..

[36]  J. Koolen,et al.  The distance-regular graphs such that all of its second largest local eigenvalues are at most one , 2011, 1102.4292.

[37]  Edwin R. Hancock,et al.  Fast depth-based subgraph kernels for unattributed graphs , 2016, Pattern Recognit..

[38]  Pascal Frossard,et al.  The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains , 2012, IEEE Signal Processing Magazine.

[39]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[40]  Willem H. Haemers,et al.  Spectra of Graphs , 2011 .