Evolutionary Network Embedding Preserving Both Local Proximity and Community Structure

The complex network is an important tool to represent relational data in nature and human society, which has been widely applied in various real-world application scenarios. A key issue for analyzing the features of networks is to represent the characteristic information in the network with rationality. Network embedding, attracting plenty of attention recently, aims to convert network information into a low-dimensional space while maintaining the structure and properties of the network maximally. Most of the existing network embedding methods intend to preserve the pairwise relationship or similarity between nodes, but the community structure, which is one of the most important features of complex networks, is largely ignored. In this article, we propose a novel network embedding method based on evolutionary algorithm (EA), termed as EA-NECommunity, which can preserve both the local proximity of nodes and the community structure of the network by optimizing a carefully designed objective function. The number of communities in the network can be automatically determined without any prior knowledge. Moreover, taking the intrinsic properties of the network embedding problems in mind, we design a local search operator based on multidirectional search which can effectively find feasible solutions. In the experiments, we first visualize the embedding representation obtained by different algorithms, and then use the problems of node clustering, node classification, and link prediction to further validate the quality of the embedding representation obtained. The experimental results show that EA-NECommunity outperforms other state-of-the-art algorithms on both the real life and synthetic networks.