文献类型：期刊文献

英文题名：Over-Smoothing Algorithm and Its Application to GCN Semi-supervised Classification

作者：Dai, Mingzhi[1,2]; Guo, Weibin[1]; Feng, Xiang[1,2]

机构：[1] Department of Information Science and Engineering, East China University of Science and Technology, Shanghai, China; [2] Smart City Collaborative Innovation Center, Shanghai Jiao Tong University, Shanghai, China

年份：2020

卷号：1258 CCIS

起止页码：197

外文期刊名：Communications in Computer and Information Science

收录：EI(收录号：20203609129816)

语种：英文

外文关键词：Laplace transforms - Economic and social effects - Supervised learning - Polynomials

摘要：The feature information of the local graph structure and the nodes may be over-smoothing due to the large number of encodings, which causes the node characterization to converge to one or several values. In other words, nodes from different clusters become difficult to distinguish, as two different classes of nodes with closer topological distance are more likely to belong to the same class and vice versa. To alleviate this problem, an over-smoothing algorithm is proposed, and a method of reweighted mechanism is applied to make the trade-off of the information representation of nodes and neighborhoods more reasonable. By improving several propagation models, including Chebyshev polynomial kernel model and Laplace linear 1st Chebyshev kernel model, a new model named RWGCN based on different propagation kernels was proposed logically. The experiments show that satisfactory results are achieved on the semi-supervised classification task of graph type data. ? 2020, Springer Nature Singapore Pte Ltd.