AI Paper Atlas

Research map / Graph learning / GNN architectures

Deeper Insights Into Deep Graph Convolutional Networks: Stability and Generalization

Guangrui Yang, Ming Li, Feng Han, Xiaosheng Zhuang

TPAMI 2025 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 55 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use normalized graph filter instead of random walk filter (ablation)5-layer GCN · Corageneralization gap: 1.796 -> 1.352Improved
use normalized graph filter instead of random walk filter (ablation)5-layer GCN · Citeseergeneralization gap: 3.061 -> 2.661Improved
use normalized graph filter instead of random walk filter (ablation)5-layer GCN · Pubmedgeneralization gap: 2.497 -> 1.571Improved
increase number of layers K from 1 to 5 (ablation)GCN · Cora/Citeseer/Pubmedgeneralization gapHurt
double hidden width from d=32 to 2d (ablation)5-layer GCN with normalized filter · Cora/Citeseer/Pubmedgeneralization gapHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy