Influence maximization in social networks using graph embedding and graph neural network

With the boom in technologies and mobile networks in recent years, online social networks have become an integral part of our daily lives. These virtual networks connect people worldwide and provide them excellent platforms for promoting their products and ideas. It is often the case that certain users are more influential than others present on social networks. The process of efficiently recognizing influential users to maximize a particular piece of information across a network is known as Influence Maximization (IM). In this paper, we propose a novel method of influence maximization by using the idea of graph embedding and graph neural networks. This study intends to convert the problem of influence maximization in complex networks into a pseudo-regression problem. As part of our approach, first, we employ the struc2vec node embedding to generate the embedding for every node in the network, and the obtained embedding acts as the feature for each node. The nodes and their features are then fed into a Graph Neural Network (GNN) based regressor. The labels required for training the GNN for the regression task are obtained by calculating every node’s influence under the Susceptible-Infected-Recovered (SIR) and Independent Cascade (IC) information diffusion model. After that, we select an optimal training network by performing a parametric analysis on synthetic test networks. Finally, the trained model is used to predict the probable influence of nodes on the target network. Experimental results on several real-life networks based on various evaluation metrics show that the proposed approach outperforms some of the classical and recently proposed influence maximization methods.