RG-GCN: Improved Graph Convolution Neural Network Algorithm Based on Rough Graph

作     者：Ding, Weiping Pan, Bairu Ju, Hengrong Huang, Jiashuang Cheng, Chun Shen, Xinjie Geng, Yu Hou, Tao 

作者机构：Nantong Univ Sch Informat Sci & Technol Nantong 226019 Jiangsu Peoples R China 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2022年第10卷

页      面：85582-85594页

核心收录：

基　　金：National Natural Science Foundation of China [61976120, 62006128, 62102199] Natural Science Foundation of Jiangsu Province [BK20191445] Natural Science Key Foundation of Jiangsu Education Department [21KJA510004] 

主　　题：Graph convolution neural network topological graph rough set rough graph uncertain relationship 

摘      要：The graph convolution neural network uses topological graph to portray inter-node relationships and update node features. However, the traditional topological graph can only describe the certain relationship between nodes (that is, the weight of the connecting edge is a fixed value), while ignoring the uncertainty widely existing in the real world. These uncertainties not only affect the relationship between nodes, but also affect the final classification performance of the model. In order to overcome this defect, a graph convolution neural network algorithm based on rough graph is proposed in this paper. Specifically, the algorithm first constructs a rough graph using a combination of the upper and lower approximation theory of the rough set and the edge theory of the topological graph, the paired maximum-minimum relationship values are used to characterize the uncertain relationship between nodes. Then, this paper designs an end-to-end training neural network architecture based on rough graph, the trained rough graph is fed to this neural network to update node features with these uncertain relationship. Finally, nodes are classified according to these learned node features. The experimental results on real data show that the proposed algorithm can significantly improve the accuracy of node classification compared with the traditional graph convolution neural network.