Human brain is a complex system, characterized by its astonishing dynamical neural networks that operate over a wide range of temporal and spatial scales. Particulally, neural netorks involving frontal cortex have been believed to play crucial roles in humal mental activityies. Despite numerous reports describing aberrant neural network on various types of mental disorders, the exact neurophysiological basis remains unclear. On the other hand, a new discipline called “complex netowrk science” is emerging. The complexity and network approaches to neuroimaging data have been provided cruscial insights to functional neural networks in pathological conditions. Electroencephalogram and magnetoencephalogram (E/MEG) can directly measure brain electric and magnetic fields of the cortex with excellent temporal resolution, thereby yielding insight into temporal dynamics within physiologically relevant frequency ranges. Therefore, it is well suited to measure whole‐brain neural network. In this paper, empirical E/MEG studies of the complexity and network analyses in mental disorders are presented and further discussed their future directions. There are no potential conflicts of interest to disclose.