Unified framework for complex graph-data: introducing the hybrid layered network model

Abstract Many different network models have been in use for representing relational data. These include homogeneous networks, heterogeneous networks and multilayer networks. However, none of these models are generalized enough to represent both simple and complex relational data. The present paper provides a unified model of network, namely, Hybrid Layered Network (HLN). We proved that the sets of all homogeneous, heterogeneous and multi-layered networks are subsets of the set of all HLNs, depicting the model’s generalizability. The proposed HLN is more efficient in encoding different types of nodes and edges when compared to representing the same information through heterogeneous or multilayered networks. It is found experimentally that the HLN model, when used with GNNs, improves tasks such as link prediction. In addition, we present a novel parameterized algorithm (with complexity analysis) for generating synthetic HLNs. The networks generated from our proposed algorithm are more consistent in modelling the layer-wise degree distribution of a real-world Twitter network (represented as HLN) than those generated by existing models. Moreover, we also show that our algorithm is capable of generating various multilayer and homogeneous networks. Further, we define different structural measures for HLN, namely multilayer neighborhood, degree centrality, closeness centrality and betweenness centrality. Accordingly, we established the equivalency of the proposed structural measures of HLNs with those of homogeneous, heterogeneous, and multi-layered networks.