SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.13318 · ICML · 2020

A Note on Over-Smoothing for Graph Neural Networks

Chen Cai, Yusu Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as oversmoothing 1 , has been analyzed mostly in linear cases. In this paper, we build upon previous results (Oono & Suzuki, 2019) to further analyze the over-smoothing effect in the general graph neural network architecture. We show when the weight matrix satisfies the conditions determined by the spectrum of augmented normalized Laplacian, the Dirichlet energy of embeddings will converge to zero, resulting in the loss of discriminative power. Using Dirichlet energy to measure "expressiveness" of embedding is conceptually clean; it leads to simpler proofs than (Oono & Suzuki, 2019) and can handle more non-linearities.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.13318")
get_code_for_paper("2006.13318")
have("2006.13318")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.13318.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.13318.svg)](https://syntology.ai/paper/2006.13318)

Connect an agent — have() is free.