NE-FLGC: Network Embedding Based on Fusing Local (First-Order) and Global (Second-Order) Network Structure with Node Content

This paper studies the problem of Representation Learning for network with textual information, which aims to learn low dimensional vectors for nodes by leveraging network structure and textual information. Most existing works only focus on one aspect of network structure and cannot fuse network first-order proximity, second-order proximity and textual information. In this paper, we propose a novel network embedding method NE-FLGC: Network Embedding based on Fusing Local (first-order) and Global (second-order) network structure with node Content. Especially, we adopt context-enhance method that obtains node embedding by concatenating the vector of itself and the context vectors. In experiments, we compare our model with existing network embedding models on four real-world datasets. The experimental results demonstrate that NE-FLGC is stable and significantly outperforms state-of-the-art methods.