REPRESENTATION LEARNING METHOD OF GRAPH CONVOLUTIONAL NETWORK BASED ON STRUCTURE ENHANCEMENT

Network representation learning has attracted widespread attention as a pre-processing process for some machine learning and deep learning tasks. How-ever, most existing methods only consider influence of nodes' low-order neighbors to represent them. Either nodes' high-order neighbor or the intrinsic characteris-tic attributes of nodes are ignored, leading to the effect of network representation learning that needs to be improved. This paper proposes a novel model named Structure Enhanced Graph Convolutional Network (SEGCN) to address these lim-itations. SEGCN consists of the following components, i.e., the network structure enhancement to transform weak relationship into strong relationship, the node fea-ture aggregation to fuse high-order neighbor information. Hence, the SEGCN model can simultaneously integrate network structure information, attribute information, and high-order neighbor relationships together. Experimental results for node clas-sification and node clustering on six datasets show that SEGCN achieves better effectiveness and efficiency than state-of-the-art baselines.