Over-smoothing Effect of Graph Convolutional Networks

2022/01/30 by Fang Sun, Sun, Fang
Computer Science · #Advanced Neural Network Applications #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2201.12830

openalex publication_date 2022/01/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Simplifying the Theory on Over-Smoothing
• Tackling Over-Smoothing for General Graph Convolutional Networks
• A Survey on Oversmoothing in Graph Neural Networks
• On Provable Benefits of Depth in Training Graph Convolutional Networks
• Revisiting Over-smoothing in Deep GCNs