Finding quasi core with simulated stacked neural networks

Studying networks is promising for diverse applications. We are often interested in exploring significant substructures in different types of real-life networks. Finding cliques, which denote a complete subgraph of a graph, is one such important problem in network analysis. Interestingly, many real-life networks often contain a significant number of almost (quasi) complete subgraphs, which are not entirely complete due to the presence of noise. Considering these networks as weighted adds further challenges to the problem. Finding quasi-complete subgraphs in weighted graphs has never been formally addressed. In this paper, we propose a stacked neural network model for finding out the largest quasi-complete module (core) in weighted graphs. We show the effectiveness of the proposed approach on DIMACS graphs. We also highlight its utility in analyzing scientific collaboration networks, social networks and biological networks.