Uncovering hidden nodes and hidden links in complex dynamic networks

Inferring network structures from available data has attracted much interest in network science; however, in many realistic networks, only some of the nodes are perceptible while others are hidden, making it a challenging task. In this work, we develop a method for reconstructing the network with hidden nodes and links, taking account of fast-varying noise and time-delay interactions. By calculating the correlations of available data with different derivative orders for multiple pairs of accessible nodes, analyzing and integrating the relationships between different correlations, and defining diverse hidden-node-related reconstruction motifs, we can effectively identify the hidden nodes and hidden links in the network.