Over-Smoothing Algorithm and Its Application to GCN Semi-supervised Classification

• 作者: Mingzhi Dai Weibin Guo Xiang Feng
• 来源期刊: 国际计算机前沿大会会议论文集
• 学科: 数学
• 关键词: GCN Chebyshev polynomial kernel model Laplace linear 1st Chebyshev kernel model Over-smoothing Reweighted mechanism
• 年，卷（期）: 2020,（2）
• 页码范围: 197-215
• 页数: 19页
• 分类号: O17

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 tradeoff 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.