Over-smoothing Effect of Graph Convolutional Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 17 references that are in the map. First posted on arXiv 30 Jan 2022.
Builds on
11 of 17 references.
References · 11
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2019Simplifying Graph Convolutional Networkscited by 1,477
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
- 2020Simple and Deep Graph Convolutional Networkscited by 860
- 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
- 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
- 2020Towards Deeper Graph Neural Networkscited by 296
- 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
- 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
Built on by
Citing papers per year: 2022: 1.
1 paper.