Over-smoothing Effect of Graph Convolutional Networks

2022-01-30 · Fang Sun

Over-smoothing is a severe problem which limits the depth of Graph Convolutional Networks. This article gives a comprehensive analysis of the mechanism behind Graph Convolutional Networks and the over-smoothing effect. The article proposes an upper bound for the occurrence of over-smoothing, which offers insight into the key factors behind over-smoothing. The results presented in this article successfully explain the feasibility of several algorithms that alleviate over-smoothing.

📄 PDF Abstract BibTeX arXiv:2201.12830

Code (0)

등록된 구현이 없습니다.

SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks

2021-12-22 · Weigang Lu, Yibing Zhan, Binbin Lin, Ziyu Guan 외

Graph Convolutional Networks (GCNs) suffer from performance degradation when models go deeper. However, earlier works only attributed the performance degeneration to over-smoothing. In this paper, we conduct theoretical …

Link Prediction Node Classification

SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks

2021-02-20 · Haimin Zhang, Min Xu, Guoqiang Zhang, Kenta Niwa

Graph convolutional networks have been successfully applied in various graph-based tasks. In a typical graph convolutional layer, node features are updated by aggregating neighborhood information. Repeatedly applying gra…

Graph Learning

Simple and Deep Graph Convolutional Networks

2020-07-04 · ICML 2020 1 · Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding 외

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datas…

Graph Classification Graph Regression Link Prediction Node Classification+2

Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks

2020-02-07 · Ziqing Yang, Shoudong Han, Jun Zhao

Graph convolutional network (GCN) is now an effective tool to deal with non-Euclidean data, such as social networks in social behavior analysis, molecular structure analysis in the field of chemistry, and skeleton-based …

Action Recognition Skeleton Based Action Recognition

Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective

2020-09-24 · Hongwei Zhang, Tijin Yan, Zenjun Xie, Yuanqing Xia 외

Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on t…

General Classification Node Classification