AI Paper Atlas

Research map / Graph learning / GNN architectures

DRGCN: Dynamic Evolving Initial Residual for Deep Graph Convolutional Networks

Lei Zhang, Xiaodong Yan, Jianshan He, Ruopeng Li, Wei Chu

AAAI 2023 · Graph learning › GNN architectures · approach: Deep graph convolution and simplification · 12 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
Add node-personalized dynamic residual weights (ablation)GCNII · Cora, 2 layersaccuracy: 84.6 -> 85.4Improved
Add node-personalized dynamic residual weights (ablation)GCNII · Cora, 64 layersaccuracy: 87.1 -> 86.9Hurt
Add an evolving block to model layer correlation in residual weights (ablation)Dynamic-residual GCNII (+Dyn) · Cora, 64 layersaccuracy: 86.9 -> 87.5Improved
Add data augmentation (ablation)DRGCN · Cora, 64 layersaccuracy: 87.5 -> 88.1Improved
Add data augmentationDRGCN · Cora, 140 training nodesaccuracy: 58.0 -> 85.8Improved
Use mini-batch instead of full-batch trainingDRGAT · Coramemory: 1.28 -> 0.49Improved
Use mini-batch instead of full-batch trainingDRGAT · Coraaccuracy: 88.20 -> 88.00No clear effect
Use mini-batch instead of full-batch trainingDRGAT · ogbn-arxivmemory: 7.42 -> 2.27Improved
Use mini-batch instead of full-batch trainingDRGAT · ogbn-arxivaccuracy: 74.16 -> 74.08No clear effect
Add GIANT-XRT pretrained featuresDRGAT · ogbn-arxivtest accuracy: 74.16 ± 0.07 -> 76.11 ± 0.09Improved
Add self-knowledge distillationDRGAT+GIANT-XRT · ogbn-arxivtest accuracy: 76.11 ± 0.09 -> 76.33 ± 0.08Improved

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