Self-affine Fractals Embedded in Spectra of Complex Networks

The scaling properties of spectra of real world complex networks are studied by using the wavelet transform. It is found that the spectra of networks are multifractal. According to the values of the long-range correlation exponent, the Hust exponent $H$, the networks can be classified into three types, namely, $H>0.5$, $H=0.5$ and $H<0.5$. All real world networks considered belong to the class of $H \ge 0.5$, which may be explained by the hierarchical properties.